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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing characteristics or qualities of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otin
    -0.71
    arf
    -0.68
    Ô
    -0.67
    swick
    -0.66
    weeney
    -0.64
    ás
    -0.64
    earance
    -0.63
    antha
    -0.63
    xus
    -0.62
    erity
    -0.61
    POSITIVE LOGITS
     alike
    1.56
     respectively
    1.24
     depending
    0.91
     enough
    0.78
     sounding
    0.76
     nonetheless
    0.75
    depending
    0.73
     compared
    0.71
    .
    0.69
    ;
    0.68
    Act Density 0.139%

    No Known Activations