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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific structured phrases and relationships in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.16
    ripp
    -0.15
    .scalablytyped
    -0.14
    dux
    -0.14
    zyst
    -0.14
    ibold
    -0.14
    renc
    -0.14
    rana
    -0.13
    á»ĵn
    -0.13
    akhir
    -0.13
    POSITIVE LOGITS
     Rebel
    0.14
     strapon
    0.13
    886
    0.13
    443
    0.13
    ofi
    0.12
    844
    0.12
    اÙĦÙī
    0.12
     disadv
    0.12
    373
    0.12
    igo
    0.12
    Act Density 0.153%

    No Known Activations