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

    Neuronpedia

    INDEX
    Explanations

    phrases related to operational benefits and risks

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fighter
    -0.67
     rehearsal
    -0.64
    edient
    -0.64
     guarding
    -0.62
     BAL
    -0.60
     striving
    -0.60
    hran
    -0.60
     Moz
    -0.60
     cheating
    -0.59
     Mant
    -0.59
    POSITIVE LOGITS
    't
    1.51
    adian
    1.25
    berra
    1.20
    NOT
    0.98
    vas
    0.96
     attest
    0.95
    isters
    0.95
     afford
    0.90
    nery
    0.86
     be
    0.85
    Act Density 0.173%

    No Known Activations