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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¿Ĵ
    -0.15
    mong
    -0.14
    vik
    -0.13
    ething
    -0.13
    TableViewCell
    -0.13
    JsonValue
    -0.13
    GLfloat
    -0.13
    etal
    -0.13
    _singleton
    -0.13
    reon
    -0.13
    POSITIVE LOGITS
    ieber
    0.20
     based
    0.20
    based
    0.18
     those
    0.17
     none
    0.16
     quello
    0.15
     Based
    0.15
     called
    0.15
    either
    0.15
     via
    0.15
    Act Density 0.237%

    No Known Activations