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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aram
    -0.18
    icker
    -0.17
    İ·
    -0.16
    ascal
    -0.15
    alle
    -0.15
    iked
    -0.15
    еÑģи
    -0.15
    ARAM
    -0.15
    aa
    -0.14
    MinMax
    -0.14
    POSITIVE LOGITS
    ioni
    0.18
    олиÑĤ
    0.17
     satellites
    0.14
    conti
    0.14
     Hammer
    0.14
    elez
    0.14
    agraph
    0.14
    ombres
    0.14
    nio
    0.14
    uria
    0.13
    Act Density 0.000%

    No Known Activations