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

    Neuronpedia

    INDEX
    Explanations

    directional terms and references to navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lest
    -0.15
    utr
    -0.15
    ledge
    -0.15
    /interface
    -0.14
    inson
    -0.14
     Hole
    -0.14
     hole
    -0.14
     Wide
    -0.14
     majority
    -0.14
    asaki
    -0.14
    POSITIVE LOGITS
    ward
    0.28
    wards
    0.27
    bound
    0.25
     toward
    0.21
     towards
    0.20
    Bound
    0.19
    WARDS
    0.17
    WARD
    0.17
     direction
    0.17
    Ñıж
    0.15
    Act Density 0.024%

    No Known Activations