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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing textures or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEA
    -0.87
    imester
    -0.72
    YN
    -0.72
    VL
    -0.71
    igate
    -0.71
    INC
    -0.69
    Ĥ¬
    -0.69
    OTOS
    -0.69
    RF
    -0.68
    avia
    -0.68
    POSITIVE LOGITS
    ness
    0.91
     eyed
    0.91
     conco
    0.89
     little
    0.87
     affair
    0.87
     old
    0.86
     blob
    0.83
     sounding
    0.82
     goodness
    0.82
     cheeks
    0.79
    Act Density 0.155%

    No Known Activations