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

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    various forms of contractions or possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rematch
    -0.67
     cycle
    -0.67
     eclipse
    -0.65
    rador
    -0.63
     contrast
    -0.61
    conservancy
    -0.61
     handc
    -0.60
     transpl
    -0.60
    isphere
    -0.59
     coupled
    -0.59
    POSITIVE LOGITS
    Allah
    0.91
    atri
    0.87
    Cause
    0.87
    Mech
    0.85
    MIC
    0.82
    Angelo
    0.82
    Brien
    0.81
    nai
    0.75
    arak
    0.75
    Malley
    0.74
    Act Density 0.044%

    No Known Activations