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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating intention or plan

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intention or plans to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cit
    -0.78
    acks
    -0.76
    aud
    -0.75
    ammy
    -0.64
    amping
    -0.64
    amps
    -0.63
    bury
    -0.62
    yards
    -0.62
    acked
    -0.62
    aura
    -0.61
    POSITIVE LOGITS
    orial
    0.76
    ments
    0.75
    chwitz
    0.74
    ratulations
    0.72
     intend
    0.69
    л
    0.69
     intends
    0.69
    folios
    0.68
     Parenthood
    0.67
    mber
    0.67
    Act Density 0.013%

    No Known Activations