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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that convey a sense of completion or interruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nar
    -0.16
    ider
    -0.16
    BuilderInterface
    -0.16
    ÑĢоÑī
    -0.15
    feeds
    -0.14
    éĤ¦
    -0.14
    _tF
    -0.14
    ειο
    -0.14
    apis
    -0.13
    cestor
    -0.13
    POSITIVE LOGITS
     Br
    0.15
     recip
    0.14
     bel
    0.14
     br
    0.14
     dummy
    0.14
     Pl
    0.14
    EDA
    0.14
     LIB
    0.14
     Andreas
    0.14
    дам
    0.14
    Act Density 0.004%

    No Known Activations