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

    Neuronpedia

    INDEX
    Explanations

    C++ data types and class structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SupportedContent
    -0.17
    Scaler
    -0.16
    ãĤ¤ãĤ¯
    -0.15
    platz
    -0.15
    vette
    -0.15
    zı
    -0.14
    orsch
    -0.14
    atoria
    -0.14
    ponge
    -0.14
    ahat
    -0.14
    POSITIVE LOGITS
    ::
    0.47
     ::
    0.26
    ::~
    0.25
    ::_
    0.22
    &
    0.20
    ::{
    0.20
    *
    0.20
    ::↵
    0.20
    ::-
    0.19
     BOOST
    0.19
    Act Density 0.031%

    No Known Activations