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

    Neuronpedia

    INDEX
    Explanations

    terms and references relating to "public" or "pub" contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.74
    usercontent
    -0.69
     Mansfield
    -0.67
    lini
    -0.65
     Goodrich
    -0.65
    EndInit
    -0.65
     kant
    -0.64
    ölkerung
    -0.63
    ABL
    -0.63
    ान
    -0.62
    POSITIVE LOGITS
    pub
    1.93
     Pub
    1.85
     pub
    1.83
    Pub
    1.69
     PUB
    1.58
     pubs
    1.31
    PUB
    1.25
    Pubs
    1.19
     PUBL
    1.15
     publi
    1.10
    Act Density 0.043%

    No Known Activations