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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leading or direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mach
    -0.68
    ager
    -0.62
    issan
    -0.62
    ctic
    -0.60
    agen
    -0.59
    pton
    -0.59
    cube
    -0.59
     Tar
    -0.59
    afort
    -0.59
    rehensive
    -0.57
    POSITIVE LOGITS
    better
    0.88
     Leading
    0.80
    ĸļ
    0.78
    lead
    0.77
    Īè
    0.73
     leads
    0.71
    ļéĨĴ
    0.68
    wcs
    0.68
    :{
    0.67
    leading
    0.66
    Act Density 0.011%

    No Known Activations