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

    Neuronpedia

    INDEX
    Explanations

    references to mountains and mountainous terrain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.76
     DELHI
    -0.69
     مرئيه
    -0.69
    躇
    -0.66
     BEDROOM
    -0.65
     arşivlendi
    -0.65
    ładka
    -0.61
    addPreferredGap
    -0.61
    Geplaatst
    -0.61
     makeStyles
    -0.61
    POSITIVE LOGITS
     mountain
    2.42
     mountains
    2.31
     Mountain
    2.27
    Mountain
    2.13
     Mountains
    2.06
    mountain
    2.00
     MOUNTAIN
    1.95
    mountains
    1.83
    Mountains
    1.81
     mountainous
    1.77
    Act Density 0.079%

    No Known Activations