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

    Neuronpedia

    INDEX
    Explanations

    connections between facts and conditions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.76
     pleaſure
    -0.73
    SBATCH
    -0.73
     asunder
    -0.72
     ujednoznacz
    -0.71
    θη
    -0.69
    Personensuche
    -0.69
     FontFamily
    -0.69
    LookAnd
    -0.68
    :✨
    -0.68
    POSITIVE LOGITS
    ction
    0.84
    ctive
    0.81
    ctions
    0.77
    numberOf
    0.63
     numberOf
    0.59
    NumberOf
    0.59
     organic
    0.57
    ctional
    0.57
    Actions
    0.54
     nano
    0.54
    Act Density 0.191%

    No Known Activations