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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moving" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oys
    -0.74
    lain
    -0.72
    oured
    -0.68
    sung
    -0.68
    omial
    -0.66
    vous
    -0.64
    conn
    -0.64
    ificial
    -0.62
    ingo
    -0.62
    vale
    -0.62
    POSITIVE LOGITS
     forward
    0.92
    brates
    0.84
     toward
    0.82
    Motion
    0.81
     towards
    0.79
     away
    0.74
    ets
    0.74
    peed
    0.72
    overs
    0.71
     motions
    0.71
    Act Density 0.041%

    No Known Activations