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

    Neuronpedia

    INDEX
    Explanations

    directional language related to movement and position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Filler
    -0.58
    торая
    -0.53
    </>
    -0.51
     he
    -0.51
     she
    -0.50
    witzerland
    -0.48
    ANCO
    -0.48
     Reed
    -0.48
    tellte
    -0.48
     présence
    -0.48
    POSITIVE LOGITS
     towards
    0.83
    towards
    0.82
     toward
    0.80
     ویکی‌پدیای
    0.75
    ParallelGroup
    0.75
    toward
    0.72
     westward
    0.72
    ConstraintMaker
    0.69
     outwards
    0.69
    rungsseite
    0.68
    Act Density 0.235%

    No Known Activations