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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the special character âĢĵ

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orts
    -0.78
    ruck
    -0.74
    angu
    -0.71
    ient
    -0.71
    ...]
    -0.70
    odcast
    -0.67
    olls
    -0.65
    itsu
    -0.64
    eks
    -0.63
    oky
    -0.63
    POSITIVE LOGITS
    ––
    1.04
    ————
    0.97
    ————————
    0.91
     namely
    0.90
     ie
    0.86
     albeit
    0.82
    _-
    0.82
     hence
    0.79
     aka
    0.77
    _>
    0.76
    Act Density 0.098%

    No Known Activations