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

    Neuronpedia

    INDEX
    Explanations

    directional terms related to navigation or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eclared
    -0.54
    hring
    -0.46
     coeur
    -0.46
     correctes
    -0.45
     His
    -0.42
    hä
    -0.42
    στό
    -0.42
     con
    -0.42
     
    -0.42
    pted
    -0.41
    POSITIVE LOGITS
    izontal
    0.80
     direita
    0.75
     يتيمه
    0.74
    clockwise
    0.73
    resizingMask
    0.72
    TintMode
    0.72
     esquerda
    0.71
     stanga
    0.67
    expandindo
    0.67
     CanadaChoose
    0.66
    Act Density 0.303%

    No Known Activations