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

    Neuronpedia

    INDEX
    Explanations

    strong action verbs or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.84
    involved
    -0.65
    attribute
    -0.63
    affle
    -0.63
    eve
    -0.63
    assian
    -0.62
    enter
    -0.60
    aterial
    -0.60
    etermin
    -0.60
    earable
    -0.60
    POSITIVE LOGITS
     chiefly
    0.89
     by
    0.88
     jointly
    0.84
     anonymously
    0.83
     principally
    0.81
     hereby
    0.81
     annually
    0.80
     separately
    0.80
     herein
    0.79
     anew
    0.78
    Act Density 0.160%

    No Known Activations