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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making processes or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĭãģ®
    -0.16
    ãĤīãģĦ
    -0.15
    521
    -0.15
    920
    -0.14
    umeric
    -0.14
    uild
    -0.14
    oca
    -0.14
    icks
    -0.14
    ois
    -0.14
    anship
    -0.14
    POSITIVE LOGITS
    jong
    0.16
     âĨĴ↵↵
    0.15
     exactly
    0.14
    elah
    0.14
    emies
    0.13
    kte
    0.13
     precisely
    0.13
    emi
    0.13
    onth
    0.13
    _keeper
    0.13
    Act Density 0.146%

    No Known Activations