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

    Neuronpedia

    INDEX
    Explanations

    common phrases and expressions used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sandbox
    -0.15
    ForObject
    -0.15
    imens
    -0.15
    adden
    -0.14
    oras
    -0.14
    ilate
    -0.14
    ees
    -0.14
    Enumerable
    -0.14
    panied
    -0.14
    bows
    -0.14
    POSITIVE LOGITS
    æ³½
    0.17
    olu
    0.15
    aired
    0.15
    usk
    0.15
    MUX
    0.14
    olio
    0.14
    itra
    0.14
    atel
    0.14
    AMED
    0.14
     Conditional
    0.14
    Act Density 0.034%

    No Known Activations