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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its various forms indicating actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ByVersion
    -0.14
    enary
    -0.14
     âĵĺ
    -0.14
    UGC
    -0.13
    gas
    -0.13
    uld
    -0.13
    eah
    -0.13
    azes
    -0.13
    reate
    -0.13
    urt
    -0.13
    POSITIVE LOGITS
     sat
    0.21
    sat
    0.20
     trans
    0.19
     saturation
    0.18
     sit
    0.18
     Sat
    0.18
     sits
    0.17
     transcription
    0.17
    exp
    0.17
    Sat
    0.17
    Act Density 0.043%

    No Known Activations