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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "let" followed by related phrases that indicate limitations or exclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cill
    -0.73
    acci
    -0.64
    ottest
    -0.62
    esi
    -0.62
    ombat
    -0.62
     encount
    -0.62
    assian
    -0.59
    ird
    -0.56
    ole
    -0.55
    idian
    -0.55
    POSITIVE LOGITS
     alone
    1.54
    tered
    0.85
     Alone
    0.83
    ting
    0.83
    tering
    0.77
     aside
    0.75
    downs
    0.73
    ingly
    0.68
     loose
    0.68
     us
    0.67
    Act Density 0.015%

    No Known Activations