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

    Neuronpedia

    INDEX
    Explanations

    words related to movement and action

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the syllable "ro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hawks
    -0.59
     Grayson
    -0.57
     above
    -0.57
     electron
    -0.56
    RON
    -0.56
     Crit
    -0.56
     Eliot
    -0.55
     responsibility
    -0.54
     Normandy
    -0.54
     guilt
    -0.53
    POSITIVE LOGITS
    tted
    1.21
    oster
    1.19
    ving
    1.17
    asting
    1.09
    dding
    1.09
    aches
    1.05
    sin
    1.00
    sy
    0.99
    cks
    0.97
    ping
    0.96
    Act Density 0.018%

    No Known Activations