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

    Neuronpedia

    INDEX
    Explanations

    instructions or requirements related to performing tasks or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.17
    kees
    -0.16
     Bip
    -0.16
    åİļ
    -0.15
    uggy
    -0.15
    tam
    -0.15
    Stride
    -0.14
     Chunk
    -0.14
    842
    -0.14
    æIJ
    -0.14
    POSITIVE LOGITS
     curves
    0.42
     turns
    0.41
     curve
    0.40
     Turns
    0.36
     Curve
    0.35
     bends
    0.33
     sharp
    0.33
     corners
    0.33
    curve
    0.33
     turn
    0.32
    Act Density 0.128%

    No Known Activations