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

    Neuronpedia

    INDEX
    Explanations

    words related to "information" or "infidelity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    monds
    -0.16
    vt
    -0.16
    erot
    -0.16
     Benton
    -0.15
    å¶
    -0.15
    िà¤ĸ
    -0.15
    pering
    -0.14
    aping
    -0.14
    venues
    -0.14
    abh
    -0.14
    POSITIVE LOGITS
     inf
    0.37
     Inf
    0.36
    Inf
    0.32
     INF
    0.27
    idelity
    0.24
    rastructure
    0.23
    -inf
    0.23
    idel
    0.23
    inf
    0.23
    .Inf
    0.22
    Act Density 0.013%

    No Known Activations