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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLS
    -0.15
    ôn
    -0.15
     è¦
    -0.14
    eton
    -0.14
    Äįan
    -0.14
    onom
    -0.14
    ULSE
    -0.14
     thân
    -0.14
    vio
    -0.14
    chap
    -0.14
    POSITIVE LOGITS
     capacity
    0.28
     lifetime
    0.27
     stead
    0.27
     entirety
    0.26
     haste
    0.25
     quest
    0.23
     bid
    0.22
     attempt
    0.22
     eyes
    0.22
     spare
    0.22
    Act Density 0.107%

    No Known Activations