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

    Neuronpedia

    INDEX
    Explanations

    actions related to movement and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.63
    lismo
    -0.51
     muna
    -0.47
     vertre
    -0.46
     criteria
    -0.45
    ثیر
    -0.45
     ["",
    -0.44
     mourut
    -0.44
    aryti
    -0.43
     fossa
    -0.42
    POSITIVE LOGITS
     towards
    1.26
     toward
    1.23
    towards
    1.21
    toward
    1.18
     Towards
    1.03
     Toward
    1.02
    Towards
    0.94
     TOW
    0.85
    Toward
    0.84
     menuju
    0.75
    Act Density 0.119%

    No Known Activations