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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collective actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dealer
    -0.65
     judgement
    -0.60
    soever
    -0.57
     Britann
    -0.56
     Wrap
    -0.55
    oda
    -0.55
     Bride
    -0.54
     Paradise
    -0.53
     Lod
    -0.53
     judgment
    -0.53
    POSITIVE LOGITS
     underway
    1.13
     undertaken
    1.03
     expended
    0.97
     spearheaded
    0.97
     effort
    0.96
     efforts
    0.96
     toward
    0.95
    mental
    0.85
     aimed
    0.83
     towards
    0.83
    Act Density 0.066%

    No Known Activations