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

    Neuronpedia

    INDEX
    Explanations

    names or handles on a social media platform

    oai_token-act-pair · gpt-3.5-turbo

    frequent uses of names and social accounts related to discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cised
    -0.65
    380
    -0.65
    ".[
    -0.65
    zees
    -0.65
    "],
    -0.63
    ingen
    -0.60
    cffff
    -0.59
    ipl
    -0.59
     symbolic
    -0.59
     catast
    -0.59
    POSITIVE LOGITS
     @
    2.20
     (@
    1.52
    @
    1.50
     "@
    1.44
     @@
    1.21
     <@
    1.16
    @@@@
    0.96
    @@
    0.95
     <+
    0.94
     ||
    0.92
    Act Density 0.037%

    No Known Activations