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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or connections between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.40
    ÏĤ
    -0.21
    Ùĩ
    -0.20
    sÃŃ
    -0.19
    sburg
    -0.19
    slope
    -0.19
    ska
    -0.18
    sı
    -0.17
    sar
    -0.17
    sik
    -0.16
    POSITIVE LOGITS
    ingle
    0.15
    andal
    0.15
    andex
    0.14
    rone
    0.14
    ĭ
    0.14
    servername
    0.14
    oll
    0.14
    ULSE
    0.13
    oad
    0.13
    atch
    0.13
    Act Density 0.048%

    No Known Activations