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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity and direction in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     odv
    -0.16
    CLU
    -0.15
    agina
    -0.15
    ould
    -0.14
    аÑĢод
    -0.14
     kvinnor
    -0.14
    anc
    -0.14
     mastur
    -0.14
     [$
    -0.13
    abbo
    -0.13
    POSITIVE LOGITS
     readers
    0.17
     Readers
    0.16
     YA
    0.15
     Tumblr
    0.15
     tumblr
    0.15
     queer
    0.15
     teens
    0.14
    Tumblr
    0.14
     volume
    0.14
     trope
    0.14
    Act Density 0.002%

    No Known Activations