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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movements and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.15
    /from
    -0.15
    acons
    -0.15
    ifers
    -0.15
    ahren
    -0.14
    editary
    -0.14
    uja
    -0.14
    zers
    -0.14
    /Core
    -0.14
    amu
    -0.14
    POSITIVE LOGITS
     away
    0.38
     down
    0.35
     out
    0.32
     off
    0.31
     up
    0.30
     into
    0.28
     aside
    0.26
     through
    0.25
     forth
    0.25
     back
    0.23
    Act Density 0.379%

    No Known Activations