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

    Neuronpedia

    INDEX
    Explanations

    the word "Sh" accompanied by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "Sh" and its variations, indicating a focus on a specific subject or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.76
     Ajax
    -0.75
    anwhile
    -0.75
    etheless
    -0.73
    ãģĨ
    -0.72
    ãĥ¼ãĥĨ
    -0.72
     fencing
    -0.71
    é¾įå¥ij士
    -0.71
     numbered
    -0.69
    CAST
    -0.68
    POSITIVE LOGITS
    ooting
    1.19
    allow
    1.13
    orts
    1.07
    attered
    1.06
    utterstock
    1.05
    apeshifter
    1.05
    atters
    1.05
    uff
    1.04
    irts
    1.03
    ackle
    1.03
    Act Density 0.031%

    No Known Activations