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

    Neuronpedia

    INDEX
    Explanations

    references to pronouns and their associated forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.16
    worthy
    -0.15
    ongs
    -0.14
     doz
    -0.14
    996
    -0.13
    atik
    -0.13
    å°½
    -0.13
    tica
    -0.13
    .swift
    -0.13
    ERING
    -0.13
    POSITIVE LOGITS
    ainer
    0.15
    acente
    0.14
    dash
    0.14
    ewood
    0.14
     cit
    0.14
    antlr
    0.14
    amilia
    0.14
    rown
    0.14
    rale
    0.14
    atro
    0.14
    Act Density 0.010%

    No Known Activations