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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the character "âĢ" with varying frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.69
     limitation
    -0.68
     mutual
    -0.67
     scattering
    -0.67
     scatter
    -0.66
     parity
    -0.64
     Babel
    -0.63
     farmers
    -0.63
     Golem
    -0.62
     demoral
    -0.62
    POSITIVE LOGITS
    £
    0.99
    brother
    0.92
    sty
    0.90
    ı
    0.86
    right
    0.85
    ¹
    0.83
    acca
    0.82
    į
    0.82
    who
    0.81
    ¬
    0.81
    Act Density 0.261%

    No Known Activations