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

    Neuronpedia

    INDEX
    Explanations

    symbols and unusual character sequences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lund
    -0.16
     tabindex
    -0.16
    ä»°
    -0.15
    ammad
    -0.14
    loh
    -0.13
    buat
    -0.13
    αιν
    -0.13
    /Card
    -0.13
    ely
    -0.13
    èĤ¡
    -0.13
    POSITIVE LOGITS
     Esper
    0.29
    aj
    0.21
     Ä
    0.20
     esper
    0.20
    esper
    0.18
    anto
    0.17
    enco
    0.16
    ling
    0.16
    eo
    0.16
    ido
    0.15
    Act Density 0.001%

    No Known Activations