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

    Neuronpedia

    INDEX
    Explanations

    words related to direction and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.64
     Altman
    -0.61
    propTypes
    -0.61
    roleum
    -0.60
    ilver
    -0.59
    lück
    -0.59
    người
    -0.59
    ăn
    -0.58
    principalColumn
    -0.58
    ntlet
    -0.57
    POSITIVE LOGITS
     facing
    1.13
     Facing
    1.09
     heading
    1.08
     headed
    1.05
    Facing
    1.05
     Heading
    1.02
    facing
    1.02
    heading
    1.01
    Heading
    0.94
    headed
    0.85
    Act Density 0.079%

    No Known Activations