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

    Neuronpedia

    INDEX
    Explanations

    references to specific instances or examples in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iert
    -0.16
    arest
    -0.16
     å¦
    -0.15
    veled
    -0.14
    croft
    -0.14
    itag
    -0.14
    unsch
    -0.14
     frozen
    -0.14
    ¤í
    -0.13
    avic
    -0.13
    POSITIVE LOGITS
     undermin
    0.17
    idl
    0.15
    ABCDEFGHIJKLMNOP
    0.15
    ¾¸
    0.14
    ÑĦек
    0.14
     âĹĦ
    0.13
    /cgi
    0.13
    TZ
    0.13
    ?key
    0.13
    Disposed
    0.13
    Act Density 0.024%

    No Known Activations