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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making changes

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to planning and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.59
    DragonMagazine
    -0.54
    ItemTracker
    -0.52
    Downloadha
    -0.51
    blogspot
    -0.49
    obs
    -0.49
    Serial
    -0.47
     wont
    -0.47
     marked
    -0.46
    nih
    -0.46
    POSITIVE LOGITS
     oneself
    0.85
    enance
    0.82
    uate
    0.80
    igate
    0.75
    ISE
    0.72
     them
    0.66
    ulate
    0.66
    dress
    0.65
    itate
    0.65
     him
    0.62
    Act Density 0.699%

    No Known Activations