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

    Neuronpedia

    INDEX
    Explanations

    references to directional movements, specifically "up" and "down."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hopf
    -0.82
     Palis
    -0.77
     fuper
    -0.76
    ญิง
    -0.73
     ſtate
    -0.72
     Kuan
    -0.72
     NBS
    -0.71
     LCCN
    -0.70
     pleaſure
    -0.69
     BOC
    -0.68
    POSITIVE LOGITS
     the
    0.91
    ΕΙ
    0.67
     around
    0.66
    事儿
    0.65
    はじめに
    0.65
     Olsson
    0.64
     estekak
    0.63
     MonoBehaviour
    0.63
     our
    0.63
    évaluateur
    0.63
    Act Density 0.017%

    No Known Activations