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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "resignation" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resignation"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agog
    -0.89
    verbs
    -0.79
    acebook
    -0.74
    atomic
    -0.72
    ohyd
    -0.70
    roc
    -0.69
    orically
    -0.68
    hing
    -0.68
    acca
    -0.68
    ramid
    -0.66
    POSITIVE LOGITS
     announcement
    0.75
    ishment
    0.74
     stemming
    0.69
     clause
    0.68
     checklist
    0.68
    cffffcc
    0.68
     thereof
    0.68
    ary
    0.66
     hurdle
    0.65
     slips
    0.65
    Act Density 0.067%

    No Known Activations