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

    Neuronpedia

    INDEX
    Explanations

    special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.88
    itars
    -0.81
    drawn
    -0.70
    ipeg
    -0.69
    ivities
    -0.67
     interf
    -0.65
    ucer
    -0.65
    piring
    -0.65
     horizont
    -0.65
     lipstick
    -0.65
    POSITIVE LOGITS
    į
    0.98
    à¤
    0.84
    ULE
    0.79
    774
    0.78
    ographer
    0.76
    payer
    0.75
    £
    0.75
    «ĺ
    0.75
    APH
    0.74
    \-
    0.74
    Act Density 0.031%

    No Known Activations