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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the completion or assessment of tasks or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ych
    -0.16
     rel
    -0.15
    y
    -0.14
    便
    -0.14
     Sinh
    -0.14
     èµ·
    -0.14
    .alias
    -0.14
     bass
    -0.13
     Yong
    -0.13
     Mann
    -0.13
    POSITIVE LOGITS
    ervlet
    0.17
     previously
    0.16
    ëĿ½
    0.16
    erot
    0.16
    som
    0.15
    atatype
    0.15
    ipple
    0.15
    icks
    0.15
    _UNS
    0.14
    Previously
    0.14
    Act Density 0.240%

    No Known Activations