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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to criticism and scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    sentiments related to concern or seriousness regarding various social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzo
    -0.75
    erva
    -0.70
    ivalry
    -0.69
    oret
    -0.68
    racuse
    -0.67
    chan
    -0.66
    zl
    -0.66
     CTR
    -0.65
    LLOW
    -0.64
    heses
    -0.64
    POSITIVE LOGITS
     shove
    0.72
     unintention
    0.66
    graded
    0.64
     priority
    0.63
     jeopardy
    0.63
    qqa
    0.59
     Outer
    0.58
     contrad
    0.58
     distinctly
    0.57
    inventoryQuantity
    0.57
    Act Density 0.636%

    No Known Activations