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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or favoritism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essa
    -0.15
     exact
    -0.15
    zdy
    -0.15
    -0.14
    CodeGen
    -0.13
     thorough
    -0.13
     Exact
    -0.13
    (equalTo
    -0.13
    ød
    -0.13
     Coun
    -0.13
    POSITIVE LOGITS
    вен
    0.17
    itized
    0.16
    cratch
    0.15
    esion
    0.15
    ensem
    0.15
    mie
    0.15
    odb
    0.15
    обÑĢаз
    0.15
    -defense
    0.14
    ocked
    0.14
    Act Density 0.860%

    No Known Activations