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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with data or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONDS
    -0.16
    uced
    -0.15
    etadata
    -0.15
    浦
    -0.15
    yr
    -0.15
    iry
    -0.15
     )↵↵↵↵↵↵↵↵
    -0.14
    uda
    -0.14
    OLD
    -0.14
    hammer
    -0.14
    POSITIVE LOGITS
    habi
    0.16
     wind
    0.15
    ercul
    0.15
    éĢļ
    0.14
     stick
    0.14
    Sampler
    0.14
    mav
    0.14
    %%%%%%%%
    0.14
     Hills
    0.14
     mis
    0.13
    Act Density 0.014%

    No Known Activations