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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or events in a temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arpa
    -0.18
    oog
    -0.16
    appa
    -0.16
    edBy
    -0.15
    egin
    -0.15
    arness
    -0.15
    arser
    -0.15
    chnitt
    -0.15
    kok
    -0.15
    å¿ĥ
    -0.15
    POSITIVE LOGITS
    uplic
    0.16
     Fortress
    0.15
    agonal
    0.15
     dec
    0.15
    mented
    0.15
    инÑĥ
    0.15
    mentation
    0.14
    TAG
    0.14
    _SOCKET
    0.14
     Conc
    0.13
    Act Density 0.032%

    No Known Activations