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

    Neuronpedia

    INDEX
    Explanations

    references to significant amounts or concentrations of substances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Directions
    -0.15
    itou
    -0.14
    VERAGE
    -0.14
    uitka
    -0.14
    stras
    -0.14
    ItemSelected
    -0.13
     defaults
    -0.13
    RG
    -0.13
    linky
    -0.13
    .targets
    -0.13
    POSITIVE LOGITS
     quantities
    0.30
     amounts
    0.26
     quantity
    0.26
     doses
    0.22
     sufficient
    0.21
     proportions
    0.21
     concentrations
    0.19
    quantity
    0.19
    éĩı
    0.18
     enough
    0.17
    Act Density 0.105%

    No Known Activations