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

    Neuronpedia

    INDEX
    Explanations

    code snippets and commands

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and expressions related to programming or data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -0.39
    heid
    -0.39
     JUSTICE
    -0.39
     affair
    -0.38
    ombat
    -0.37
     uncond
    -0.36
    ajor
    -0.35
    bral
    -0.34
    morrow
    -0.34
     Shroud
    -0.34
    POSITIVE LOGITS
    ONSORED
    0.48
    atto
    0.47
    âķIJ
    0.40
     srf
    0.39
    ogether
    0.38
    aditional
    0.38
    avorite
    0.36
    ravings
    0.36
     eleph
    0.36
    anwhile
    0.35
    Act Density 3.400%

    No Known Activations