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

    Neuronpedia

    INDEX
    Explanations

    references to rankings, positions, and hierarchies within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isk
    -0.16
    blr
    -0.15
    allah
    -0.15
    ë»
    -0.14
    icha
    -0.14
    tie
    -0.14
    kee
    -0.14
     ç±
    -0.13
     aba
    -0.13
    ÙĦÙĬÙĦ
    -0.13
    POSITIVE LOGITS
     top
    1.01
    top
    0.81
    -top
    0.74
    _top
    0.67
    Top
    0.66
     Top
    0.65
    .top
    0.65
    	top
    0.65
     tops
    0.64
    顶
    0.63
    Act Density 0.157%

    No Known Activations