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

    Neuronpedia

    INDEX
    Explanations

    declarative sentences starting with "I" or "It" where the subject is expressing a personal opinion or making a statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" and related constructions in the text, indicating a focus on subject pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cruel
    -0.70
     ILCS
    -0.62
     Monthly
    -0.62
     Scand
    -0.60
     undisclosed
    -0.60
    Scroll
    -0.59
     Afterwards
    -0.57
    VERTISEMENT
    -0.56
     unparalleled
    -0.56
     suprem
    -0.55
    POSITIVE LOGITS
     merely
    1.00
    Rather
    0.87
     simply
    0.87
    gemony
    0.86
    mere
    0.79
    erville
    0.77
     just
    0.76
    Instead
    0.75
    inis
    0.75
     Nor
    0.73
    Act Density 0.189%

    No Known Activations