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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions involving movement and physical interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onym
    -0.81
    UF
    -0.80
    ocl
    -0.76
    reprene
    -0.73
    itionally
    -0.71
    ©
    -0.69
    ulz
    -0.69
    oliberal
    -0.69
    ¤
    -0.68
    ¥
    -0.66
    POSITIVE LOGITS
     whence
    0.90
     albeit
    0.83
     which
    0.81
     grinning
    0.80
     lest
    0.79
     soaking
    0.78
     while
    0.77
     although
    0.76
     flanked
    0.76
     gul
    0.75
    Act Density 0.650%

    No Known Activations