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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of ability or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.75
    n
    -0.72
    es
    -0.70
    m
    -0.63
    jspx
    -0.60
    en
    -0.58
    сомо
    -0.56
     Stern
    -0.54
    ة
    -0.52
    ge
    -0.52
    POSITIVE LOGITS
     Efq
    1.00
    izable
    1.00
    ABLE
    0.97
    able
    0.96
     Theſe
    0.96
    gable
    0.92
    tvguidetime
    0.92
     Jefus
    0.91
    chable
    0.91
     myſelf
    0.91
    Act Density 0.236%

    No Known Activations