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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement and action

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀ
    -0.71
    Ĥİ
    -0.67
     chronically
    -0.67
     criminally
    -0.66
    ļ
    -0.66
    ollo
    -0.65
    Ĥ
    -0.65
    ieg
    -0.65
    otta
    -0.65
     molten
    -0.65
    POSITIVE LOGITS
    DragonMagazine
    0.76
     Appearance
    0.75
    tons
    0.75
    eteria
    0.75
    iste
    0.69
    Poké
    0.68
     inhibitor
    0.67
    cation
    0.66
     NPCs
    0.65
     Kamp
    0.65
    Act Density 0.070%

    No Known Activations