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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Keith
    -0.15
     mainland
    -0.15
     Keith
    -0.15
    ennon
    -0.15
    logan
    -0.14
     neutr
    -0.14
     Invocation
    -0.14
    sterol
    -0.14
     sovere
    -0.14
    iais
    -0.14
    POSITIVE LOGITS
     Dickens
    0.41
    Dick
    0.31
     Victorian
    0.29
     Pip
    0.27
     Eb
    0.26
    184
    0.24
    Eb
    0.23
     Charles
    0.22
    183
    0.22
     dick
    0.22
    Act Density 0.019%

    No Known Activations