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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quate
    -0.15
    anko
    -0.15
     downward
    -0.14
    irma
    -0.14
    ltk
    -0.14
    eniable
    -0.14
    /problem
    -0.14
    bs
    -0.14
    zbek
    -0.14
     Forces
    -0.14
    POSITIVE LOGITS
     towards
    0.28
     toward
    0.28
    river
    0.25
    wind
    0.24
     through
    0.23
     into
    0.23
     past
    0.21
     onto
    0.20
    range
    0.19
    state
    0.18
    Act Density 0.055%

    No Known Activations