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

    Neuronpedia

    INDEX
    Explanations

    words that denote visual attractiveness and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catching
    -1.09
     catching
    -0.93
    Catching
    -0.78
    -0.66
    ########.
    -0.63
    OCCURRED
    -0.60
    الإنجليزية
    -0.59
     MainAxisSize
    -0.59
     catches
    -0.58
     incrí
    -0.58
    POSITIVE LOGITS
    WithMany
    0.31
     पता
    0.29
     бере
    0.29
    Along
    0.29
    }{*}{}
    0.28
    Uma
    0.27
     début
    0.26
     battle
    0.26
    Loose
    0.26
     kartą
    0.26
    Act Density 0.001%

    No Known Activations