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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.85
    Datuak
    -0.83
    ioc
    -0.82
     Kond
    -0.82
     насељу
    -0.80
    setContentType
    -0.78
    шње
    -0.77
    ức
    -0.77
    ditos
    -0.77
    StandardCharsets
    -0.76
    POSITIVE LOGITS
    Away
    2.05
     Away
    2.03
     away
    1.97
    away
    1.94
     AWAY
    1.78
    AWAY
    1.61
    aways
    1.29
    eaway
    1.07
    taway
    1.02
     awa
    0.95
    Act Density 0.063%

    No Known Activations