Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe actions or states positively in terms of execution or outcome

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives describing actions and qualities, particularly those that convey effectiveness and beauty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     willingness
    -0.76
     spoilers
    -0.73
     restraint
    -0.69
     inaction
    -0.68
     disproportion
    -0.68
     subscriptions
    -0.67
    umption
    -0.66
     tendency
    -0.66
     susceptibility
    -0.65
     restraints
    -0.64
    POSITIVE LOGITS
    ãĤ©
    0.89
     addressed
    0.83
     transitioned
    0.80
    baum
    0.79
     housed
    0.79
    mint
    0.77
     entertained
    0.77
     positioned
    0.74
     etched
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.74
    Act Density 0.111%

    No Known Activations