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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss causation and conditions related to effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruppen
    -0.45
     followed
    -0.43
     seguida
    -0.40
    ArrowToggle
    -0.40
    retanto
    -0.40
    TabStop
    -0.39
     kali
    -0.39
    ada
    -0.39
    本
    -0.37
     held
    -0.36
    POSITIVE LOGITS
    ^(@)
    0.91
    ngdoc
    0.89
    Билгалдахарш
    0.89
     Efq
    0.87
    NUMX
    0.84
    ISupport
    0.82
     $_"
    0.80
    ">:
    0.78
     Reſ
    0.77
     myſelf
    0.77
    Act Density 0.499%

    No Known Activations