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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters or themes in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iat
    -0.66
    iate
    -0.58
    hong
    -0.58
    ised
    -0.57
    hua
    -0.57
    zhen
    -0.57
    zhong
    -0.56
    aaa
    -0.56
    iw
    -0.56
    iy
    -0.55
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    in
    0.60
    u
    0.52
    SPJ
    0.50
     referrerpolicy
    0.50
    s
    0.45
     poveznice
    0.45
     estimés
    0.44
    suit
    0.44
    MemoryWarning
    0.43
    Act Density 0.349%

    No Known Activations