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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inx
    -0.15
     (*(
    -0.15
    /pkg
    -0.15
    ylon
    -0.14
    äº
    -0.14
     èī¯
    -0.13
    urd
    -0.13
    edik
    -0.13
    assing
    -0.13
     (*((
    -0.13
    POSITIVE LOGITS
     prefer
    0.29
     fancy
    0.26
    prefer
    0.25
     preference
    0.21
     Prefer
    0.21
     looking
    0.19
     Require
    0.18
     already
    0.18
     like
    0.18
     simply
    0.18
    Act Density 0.087%

    No Known Activations