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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and their attributes related to settings or environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.61
    DockStyle
    -0.57
     utafitiHapana
    -0.53
    Viewed
    -0.53
    ConfigureAwait
    -0.53
    OptionsMenu
    -0.52
    ArgsConstructor
    -0.51
    JoinTable
    -0.51
     pourrez
    -0.51
     kolei
    -0.51
    POSITIVE LOGITS
     middle
    0.76
     midst
    0.76
     distance
    0.67
     presence
    0.65
     darkness
    0.65
     shadows
    0.63
     pouring
    0.62
     heat
    0.62
     shadow
    0.61
     background
    0.60
    Act Density 0.284%

    No Known Activations