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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'e' in varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    i.e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anſ
    -0.73
     Houſe
    -0.71
     pleaſure
    -0.67
     Reſ
    -0.66
    ſelf
    -0.65
    ScopeManager
    -0.65
     bershka
    -0.64
     Conſ
    -0.63
     Majefty
    -0.63
     myſelf
    -0.63
    POSITIVE LOGITS
    <bos>
    0.57
    E
    0.57
    e
    0.56
     ggf
    0.51
    g
    0.51
    i
    0.50
    ce
    0.49
    k
    0.49
    cf
    0.48
     E
    0.47
    Act Density 0.022%

    No Known Activations