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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting indicators in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lo
    -0.60
    ))/(
    -0.59
     cap
    -0.54
    )"),
    -0.54
    zwi
    -0.54
     سكان
    -0.51
     getIs
    -0.50
    %"),
    -0.49
    )){
    -0.49
    thâu
    -0.48
    POSITIVE LOGITS
    +#+
    0.77
     يتيمه
    0.76
     utafitiHapana
    0.73
    ########.
    0.72
     purpoſe
    0.71
    adaptiveStyles
    0.69
     houſe
    0.68
     Majefty
    0.67
    ConstraintMaker
    0.67
    ſelf
    0.66
    Act Density 0.303%

    No Known Activations