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

    Neuronpedia

    INDEX
    Explanations

    requests for input or feedback in comments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that request feedback or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.67
    isky
    -0.66
    etheless
    -0.66
    ationally
    -0.65
    IED
    -0.63
    inational
    -0.63
     firefighters
    -0.62
    bush
    -0.61
    oulos
    -0.60
    irl
    -0.60
    POSITIVE LOGITS
     advance
    1.16
     regards
    1.01
     case
    0.98
     chronological
    0.94
     lieu
    0.90
     anticipation
    0.90
    lc
    0.90
     hopes
    0.90
    clusions
    0.85
     alphabet
    0.83
    Act Density 0.177%

    No Known Activations