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

    Neuronpedia

    INDEX
    Explanations

    spatial relationships and directional movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.18
    mage
    -0.15
    immel
    -0.15
    ÙIJÙħ
    -0.14
    387
    -0.14
     descended
    -0.14
     mutual
    -0.14
    ler
    -0.14
     '
    -0.14
    WithValue
    -0.14
    POSITIVE LOGITS
    wards
    0.26
     towards
    0.24
     toward
    0.24
    ward
    0.21
    /down
    0.20
    WARDS
    0.19
     into
    0.19
    onto
    0.18
     wards
    0.18
    Towards
    0.18
    Act Density 0.114%

    No Known Activations