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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contrastive phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.16
    anguages
    -0.15
    unte
    -0.14
    ibs
    -0.14
    -li
    -0.14
    reon
    -0.14
    IFT
    -0.14
    cone
    -0.14
    avo
    -0.14
    éģ
    -0.13
    POSITIVE LOGITS
    以åıĬ
    0.16
    jeme
    0.15
    idenav
    0.14
    ép
    0.14
    CTYPE
    0.14
     and
    0.14
    adaki
    0.14
    oldur
    0.14
    AndPassword
    0.14
    etik
    0.14
    Act Density 0.181%

    No Known Activations