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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a sense of realization or emphasis in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hatta
    -0.18
     eux
    -0.15
    Ø·ÙĨ
    -0.14
     whom
    -0.13
     herself
    -0.13
    ÑĢеÑī
    -0.13
    intColor
    -0.13
     him
    -0.13
     [âĢ¦
    -0.12
    ovah
    -0.12
    POSITIVE LOGITS
     there
    0.28
     it
    0.24
    there
    0.23
     they
    0.22
    ,
    0.19
    forth
    0.19
    ,it
    0.18
     we
    0.18
    they
    0.17
     ÙģØ¥ÙĨ
    0.17
    Act Density 0.310%

    No Known Activations