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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms or symbols related to equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.55
    tellations
    -0.55
    (">>
    -0.53
     GoogleFonts
    -0.52
     Lawton
    -0.52
     shovel
    -0.52
    olving
    -0.51
    oken
    -0.51
    ſhip
    -0.50
    unteering
    -0.50
    POSITIVE LOGITS
    3
    1.49
    ۳
    0.80
    ３
    0.76
    rd
    0.68
    ৩
    0.68
    ₃
    0.63
    4
    0.61
     Thirty
    0.60
     thirty
    0.59
     '../../../
    0.59
    Act Density 1.170%

    No Known Activations