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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or processes being carried out on a large scale

    oai_token-act-pair · gpt-3.5-turbo

    actions related to shutdowns, closures, and arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    whatever
    -0.67
    something
    -0.61
    yip
    -0.60
    leader
    -0.56
    comes
    -0.56
    tone
    -0.55
    erity
    -0.55
     Darius
    -0.54
     prompt
    -0.54
    bral
    -0.53
    POSITIVE LOGITS
     apiece
    0.92
     consecut
    0.90
    abouts
    0.87
     individually
    0.81
     respectively
    0.79
     nationwide
    0.79
     simultaneously
    0.78
     throughout
    0.75
     worldwide
    0.75
     besides
    0.74
    Act Density 0.348%

    No Known Activations