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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypy
    -0.15
    åĩĿ
    -0.15
    otel
    -0.14
    å²
    -0.14
    ö
    -0.14
    DBG
    -0.14
    ål
    -0.14
    ãĥ¼ãĥĵ
    -0.14
    ÑĸлÑĮ
    -0.14
    ogs
    -0.14
    POSITIVE LOGITS
    cer
    0.15
    isine
    0.15
    IZER
    0.14
    ceb
    0.14
     Dop
    0.14
    236
    0.13
    .snap
    0.13
     vess
    0.13
    atori
    0.13
    ý
    0.13
    Act Density 0.016%

    No Known Activations