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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong or emphasized actions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words related to freezing and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     builder
    -0.76
     Builder
    -0.70
     autop
    -0.68
    building
    -0.66
    spe
    -0.65
    lining
    -0.64
    Builder
    -0.62
    aught
    -0.61
     banking
    -0.60
     scanner
    -0.60
    POSITIVE LOGITS
    zing
    1.13
    zed
    1.04
    zes
    0.95
    uled
    0.94
    ze
    0.89
    ÅĤ
    0.87
    ules
    0.87
    aukee
    0.83
    inka
    0.83
    xual
    0.82
    Act Density 0.011%

    No Known Activations