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

    Neuronpedia

    INDEX
    Explanations

    terms related to limitations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.19
     himſelf
    -1.10
     purpoſe
    -1.06
     pleaſure
    -1.05
     itſelf
    -1.04
     Diſ
    -1.04
     reaſon
    -1.04
     ſeveral
    -1.01
     Efq
    -0.98
     ſche
    -0.97
    POSITIVE LOGITS
     bound
    1.03
     binding
    0.96
     bind
    0.81
     Binding
    0.81
    binding
    0.76
     bindings
    0.71
     binds
    0.68
     Bound
    0.63
     beat
    0.61
     Beat
    0.59
    Act Density 0.197%

    No Known Activations