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

    Neuronpedia

    INDEX
    Explanations

    terms related to the word "head" and its various forms and combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.90
    Allo
    -0.71
     disponibilités
    -0.70
    UNITY
    -0.69
    rungsseite
    -0.65
    ⓘ
    -0.65
    --}}
    -0.64
    miracle
    -0.64
    COLORS
    -0.64
     Lester
    -0.63
    POSITIVE LOGITS
     head
    2.56
     HEAD
    2.48
     Head
    2.46
    Head
    2.37
     heads
    2.36
    head
    2.25
    HEAD
    2.15
     Heads
    2.12
    heads
    1.98
    Heads
    1.89
    Act Density 0.042%

    No Known Activations