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

    Neuronpedia

    INDEX
    Explanations

    references to direction or movement toward a goal or endpoint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Süß
    -0.42
     enfans
    -0.41
     saja
    -0.40
    deleteItem
    -0.36
     nô
    -0.36
    ektiv
    -0.36
     Canaria
    -0.34
    الدراسه
    -0.34
     않
    -0.33
     fools
    -0.33
    POSITIVE LOGITS
     towards
    1.91
     toward
    1.88
     Toward
    1.84
    towards
    1.81
     Towards
    1.80
    toward
    1.78
    Towards
    1.73
    Toward
    1.72
     hacia
    1.29
     verso
    1.17
    Act Density 0.137%

    No Known Activations