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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     миÑĤ
    -0.15
     irr
    -0.15
    mrt
    -0.15
    ledge
    -0.15
    asa
    -0.15
    agan
    -0.15
    ÙIJÙħ
    -0.14
    alm
    -0.14
    iterate
    -0.14
     Dumpster
    -0.13
    POSITIVE LOGITS
    /down
    0.19
     towards
    0.18
    STACK
    0.16
    river
    0.15
     toward
    0.15
     into
    0.15
    wards
    0.15
    ardy
    0.14
    empo
    0.14
    ières
    0.14
    Act Density 0.051%

    No Known Activations