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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or intentions that are consequential or impactful

    oai_token-act-pair · gpt-3.5-turbo

    future-oriented modal verbs indicating potential actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.70
    ricks
    -0.69
     Gentleman
    -0.65
    cius
    -0.64
     cabinet
    -0.63
     Saying
    -0.62
    ancock
    -0.62
     Conference
    -0.62
    ourse
    -0.61
    ennett
    -0.61
    POSITIVE LOGITS
     fasc
    0.77
     conflic
    0.75
    ¿½
    0.74
     underpin
    0.72
    »Ĵ
    0.72
     culmin
    0.71
     hopefully
    0.71
     prove
    0.70
    SPONSORED
    0.69
     satisfy
    0.66
    Act Density 0.212%

    No Known Activations