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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "move"

    np_acts-logits-general · gemini-2.0-flash

    moving forward or away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vorlage
    -0.57
     oídos
    -0.55
    rides
    -0.51
    ిక
    -0.48
    iding
    -0.48
     Gesichts
    -0.48
     HasFactory
    -0.48
    IsMutable
    -0.48
    Kanpo
    -0.48
    RTCF
    -0.47
    POSITIVE LOGITS
     forward
    0.94
     away
    0.89
     mountains
    0.81
     closer
    0.81
     AWAY
    0.74
    forward
    0.72
    away
    0.72
     Mountains
    0.72
     toward
    0.72
     towards
    0.70
    Act Density 0.099%

    No Known Activations