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

    Neuronpedia

    INDEX
    Explanations

    phrases that express similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shan
    -0.16
    abis
    -0.15
    ắc
    -0.15
    ffield
    -0.14
    agoon
    -0.14
     sleeve
    -0.14
    ponce
    -0.13
    rieve
    -0.13
     FE
    -0.13
     FT
    -0.13
    POSITIVE LOGITS
    apos
    0.15
    ERY
    0.14
    orman
    0.14
     ------------------------------------------------------------------------↵
    0.14
     Eigen
    0.14
    usto
    0.13
    aid
    0.13
    Sharper
    0.13
     crossorigin
    0.13
    rupted
    0.13
    Act Density 0.018%

    No Known Activations