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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to physical appearances and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ŀ
    -4.04
    ¸
    -4.03
    Ī
    -4.03
    ļ
    -4.02
    ·¸
    -3.79
    Īĺ
    -3.77
    Ĥ
    -3.77
    ĸ´
    -3.75
    ¦
    -3.75
    ķ
    -3.74
    POSITIVE LOGITS
    bum
    1.63
    backed
    1.60
     beneath
    1.57
     marks
    1.49
     relief
    1.48
     sides
    1.48
    plasty
    1.47
    ball
    1.46
    wagen
    1.45
    horn
    1.45
    Act Density 1.466%

    No Known Activations