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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checkpoints or requirements that need to be met

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onical
    -0.18
    outes
    -0.16
    .onViewCreated
    -0.16
    REFERRED
    -0.15
    inis
    -0.15
    ahat
    -0.15
    eyse
    -0.14
    gom
    -0.14
    jang
    -0.13
    оза
    -0.13
    POSITIVE LOGITS
     tick
    0.60
     check
    0.54
     box
    0.50
     checked
    0.50
     boxes
    0.48
     Tick
    0.48
     ticks
    0.47
     checkbox
    0.47
    check
    0.45
    tick
    0.45
    Act Density 0.141%

    No Known Activations