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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate possession or association, often using the term "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Integrity
    -0.14
    ávÄĽ
    -0.14
    ac
    -0.14
    anova
    -0.14
    #/
    -0.14
     дÑĢÑĥго
    -0.14
    ikers
    -0.13
    £
    -0.13
    istine
    -0.13
    ÑĤÑĥÑĢ
    -0.13
    POSITIVE LOGITS
     few
    0.19
    uais
    0.17
    imson
    0.16
    ä¹ĥ
    0.15
    Msp
    0.15
     rare
    0.15
    Few
    0.14
    ahoma
    0.14
    ains
    0.14
    asant
    0.14
    Act Density 0.034%

    No Known Activations