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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters and patterns

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that reference research, analysis, or professional commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endeav
    -0.69
     replacements
    -0.66
     footing
    -0.64
     brunt
    -0.64
     hops
    -0.64
     Trog
    -0.64
     discipl
    -0.64
     dissu
    -0.64
     forces
    -0.63
     enforcement
    -0.63
    POSITIVE LOGITS
    ³³³
    1.27
    ³³³³³³³³
    1.25
    ³³³³³³³³³³³³³³³³
    1.19
    ³³³³
    1.11
    Posted
    1.10
    posted
    1.07
    ³³
    1.02
    Introduction
    0.96
    BBC
    0.90
    pmwiki
    0.89
    Act Density 0.497%

    No Known Activations