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

    Neuronpedia

    INDEX
    Explanations

    code snippets containing the arrow function syntax '=>' followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax associated with functions and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.95
    ipel
    -0.85
    alach
    -0.82
    unte
    -0.77
    riet
    -0.76
    hyde
    -0.74
    udes
    -0.74
    resa
    -0.74
    ooks
    -0.73
    ramer
    -0.73
    POSITIVE LOGITS
     {"
    0.84
     ({
    0.76
     nil
    0.75
     {}
    0.71
     undefined
    0.69
     none
    0.69
     Ùħ
    0.69
     infinity
    0.68
     APPLIC
    0.68
     Ø
    0.68
    Act Density 0.009%

    No Known Activations