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

    Neuronpedia

    INDEX
    Explanations

    mentions of hats or discussions related to hats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    messageInfo
    -0.53
     preferencias
    -0.53
     egent
    -0.53
    Rüyada
    -0.51
    pss
    -0.49
    Datos
    -0.49
    :
    -0.48
    Offic
    -0.47
     úl
    -0.47
     rowspan
    -0.47
    POSITIVE LOGITS
     hat
    1.62
     Hat
    1.43
    Hat
    1.41
     HAT
    1.38
    hat
    1.28
    HAT
    1.21
     hats
    1.20
    hats
    1.05
     chapeau
    1.05
     Hats
    0.99
    Act Density 0.062%

    No Known Activations