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

    Neuronpedia

    INDEX
    Explanations

    words related to movement towards a specific direction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "towards."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umm
    -0.77
    chell
    -0.69
    CD
    -0.68
    ItemImage
    -0.67
    nz
    -0.66
    RC
    -0.65
    tel
    -0.65
    cell
    -0.64
    nesia
    -0.64
    PIN
    -0.64
    POSITIVE LOGITS
     towards
    1.22
    wards
    1.08
     toward
    1.07
     Towards
    0.99
    ward
    0.90
    WARD
    0.84
     infinity
    0.77
     fulfil
    0.75
    vernment
    0.73
    itiveness
    0.73
    Act Density 0.013%

    No Known Activations