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

    Neuronpedia

    INDEX
    Explanations

    phrases comparing present and past situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mund
    -0.64
     Baron
    -0.63
     Fine
    -0.62
     Berman
    -0.59
     BDS
    -0.58
     Brig
    -0.58
    Sil
    -0.57
     Barrett
    -0.57
     Torn
    -0.57
     Ward
    -0.57
    POSITIVE LOGITS
     ought
    0.91
    should
    0.88
     did
    0.79
    ikh
    0.76
     normally
    0.75
     predec
    0.74
     SHOULD
    0.73
     deserved
    0.73
     should
    0.72
    enth
    0.71
    Act Density 0.119%

    No Known Activations