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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions or movement in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icol
    -0.17
    ovel
    -0.15
     Nim
    -0.15
    ritch
    -0.15
    anna
    -0.15
     hon
    -0.15
    anim
    -0.14
    éħ
    -0.14
     Coch
    -0.14
     ole
    -0.14
    POSITIVE LOGITS
    adier
    0.18
     standpoint
    0.16
    forth
    0.15
     вок
    0.15
    chnitt
    0.15
     infix
    0.15
     perspectives
    0.14
    oom
    0.14
    κÏħ
    0.14
    ±ä¹IJ
    0.14
    Act Density 0.055%

    No Known Activations