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

    Neuronpedia

    INDEX
    Explanations

    numbers with a plus sign preceding them

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with statistical or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutherland
    -0.74
    ©¶æ
    -0.74
    onite
    -0.72
    vey
    -0.71
    anium
    -0.70
    ãĤ©
    -0.70
     Winc
    -0.70
     Grimes
    -0.69
    ning
    -0.68
     Stub
    -0.68
    POSITIVE LOGITS
    /-
    1.25
     IMAGES
    0.89
    -+
    0.78
    /+
    0.77
    plus
    0.75
    ordinary
    0.73
    cffffcc
    0.73
    ishly
    0.72
    #$
    0.72
    scl
    0.71
    Act Density 0.008%

    No Known Activations