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

    Neuronpedia

    INDEX
    Explanations

    concepts related to prior conditions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lk
    -0.17
    este
    -0.15
    uster
    -0.15
    aber
    -0.14
    erm
    -0.14
    SEG
    -0.14
    ttp
    -0.14
     record
    -0.13
    bero
    -0.13
    berger
    -0.13
    POSITIVE LOGITS
    annis
    0.17
    ardu
    0.15
    odyn
    0.15
    asha
    0.14
     sond
    0.14
    opsis
    0.14
    .pack
    0.14
    éry
    0.14
     onBind
    0.14
    .intellij
    0.14
    Act Density 0.015%

    No Known Activations