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

    Neuronpedia

    INDEX
    Explanations

    roles and titles associated with leadership and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     be
    -0.64
    เป็น
    -0.63
     me
    -0.55
     ni
    -0.51
    ap
    -0.51
    br
    -0.50
    k
    -0.50
    uk
    -0.50
    hw
    -0.50
     ஆ
    -0.49
    POSITIVE LOGITS
     فريبيس
    1.05
     lenker
    0.90
     Efq
    0.83
    FunctionFlags
    0.81
     pleaſure
    0.77
    ^(@)
    0.76
    TargetException
    0.76
     cref
    0.75
    ſelf
    0.74
     AttributeSet
    0.73
    Act Density 0.404%

    No Known Activations