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

    Neuronpedia

    INDEX
    Explanations

    words related to accolades and praises

    oai_token-act-pair · gpt-3.5-turbo

    instances of excitement or joy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acia
    -0.80
    puter
    -0.74
    ible
    -0.74
    itri
    -0.72
    ances
    -0.71
     Nadu
    -0.69
    pering
    -0.68
    iance
    -0.67
    BIP
    -0.65
     Impossible
    -0.64
    POSITIVE LOGITS
    ^^^^
    1.19
    ^^
    0.88
    hammad
    0.74
    vernment
    0.73
    nton
    0.72
    orters
    0.72
    ^
    0.66
    gio
    0.66
     Schwarz
    0.66
    ~~~~~~~~
    0.65
    Act Density 0.020%

    No Known Activations