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

    Neuronpedia

    INDEX
    Explanations

    connections or relationships in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     S
    -1.03
     J
    -0.98
     T
    -0.94
    o
    -0.93
     N
    -0.92
    S
    -0.92
     K
    -0.91
     D
    -0.90
     P
    -0.89
    E
    -0.89
    POSITIVE LOGITS
     themſelves
    1.63
     myſelf
    1.58
     itſelf
    1.55
     pleaſure
    1.48
    ſelves
    1.46
     ་་
    1.46
     Theſe
    1.44
     Monfieur
    1.44
     Efq
    1.41
     ―――――
    1.41
    Act Density 1.024%

    No Known Activations