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

    Neuronpedia

    INDEX
    Explanations

    references to geographical features or inclines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.45
     للاسماء
    -0.41
     Sov
    -0.40
     supli
    -0.40
     raiſ
    -0.40
    Климат
    -0.39
     houſe
    -0.38
    TemporalType
    -0.36
     للمعارف
    -0.36
     poffe
    -0.35
    POSITIVE LOGITS
     downhill
    0.60
     uphill
    0.60
     hillside
    0.57
     slope
    0.55
     Slope
    0.54
    Slope
    0.53
    afficheront
    0.52
     steep
    0.52
     slopes
    0.50
     landslide
    0.48
    Act Density 0.266%

    No Known Activations