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

    Neuronpedia

    INDEX
    Explanations

    directional and positional descriptions related to movement and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.55
    Filler
    -0.51
    NewUrlParser
    -0.48
    所在地
    -0.48
    couvrir
    -0.48
    つき
    -0.47
    sburg
    -0.47
    付き
    -0.46
    quity
    -0.46
     situ
    -0.46
    POSITIVE LOGITS
     towards
    0.79
    towards
    0.77
     toward
    0.74
     outwards
    0.71
     westward
    0.70
     inward
    0.69
     downwards
    0.68
     outward
    0.67
     myſelf
    0.66
     beyond
    0.66
    Act Density 0.357%

    No Known Activations