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

    Neuronpedia

    INDEX
    Explanations

    words related to direction or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating directionality or movement toward a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cats
    -0.71
    cod
    -0.71
    tel
    -0.70
    crew
    -0.68
    iasis
    -0.68
    drivers
    -0.68
    umm
    -0.68
    cu
    -0.67
    chell
    -0.67
    tele
    -0.65
    POSITIVE LOGITS
    WARD
    0.97
    wards
    0.95
     towards
    0.89
    ward
    0.86
     toward
    0.85
     Towards
    0.81
     infinity
    0.75
     fulfil
    0.75
    rontal
    0.72
    itiveness
    0.71
    Act Density 0.015%

    No Known Activations