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

    Neuronpedia

    INDEX
    Explanations

    punctuation and questioning elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ElementType
    -0.15
    ÅĻet
    -0.15
    TokenType
    -0.15
    ARSER
    -0.14
    vangst
    -0.14
     Ø£ØŃ
    -0.14
    Hang
    -0.14
    -anchor
    -0.14
    orem
    -0.14
    atham
    -0.14
    POSITIVE LOGITS
    çķ
    0.15
    imas
    0.15
     Rehab
    0.14
    μιÏĥ
    0.14
    ania
    0.14
    ery
    0.14
    estre
    0.14
     Marcel
    0.13
    iman
    0.13
     Maul
    0.13
    Act Density 0.063%

    No Known Activations