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

    Neuronpedia

    INDEX
    Explanations

    characters expressing concern or emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.60
     (
    -0.52
     =>
    -0.52
    ValueStyle
    -0.51
     (“
    -0.49
    ValueGenerated
    -0.48
    aguer
    -0.48
     posteriormente
    -0.48
    drawSprites
    -0.47
    typically
    -0.47
    POSITIVE LOGITS
    —”
    0.86
    …"
    0.86
    ."
    0.81
    …”
    0.80
    -”
    0.78
    ..."
    0.78
    DockStyle
    0.77
    ...”
    0.77
    ?"
    0.76
    !"
    0.75
    Act Density 0.358%

    No Known Activations