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

    Neuronpedia

    INDEX
    Explanations

    phrases related to engagement and involvement in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "not" or negation words

    np_acts-logits-general · gemini-2.0-flash

    superficial, not reactive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     virke
    -0.58
     véritables
    -0.57
     kaarangay
    -0.57
    RenderAtEndOf
    -0.55
     irl
    -0.53
     clearColor
    -0.52
    Özel
    -0.51
    Seriously
    -0.51
     prawdzi
    -0.51
     særlig
    -0.51
    POSITIVE LOGITS
     superfic
    0.89
     reactive
    0.87
     merely
    0.85
     silo
    0.82
     Reactive
    0.82
     superficial
    0.81
     rote
    0.80
     haphazard
    0.77
    なんとなく
    0.77
     lip
    0.76
    Act Density 0.498%

    No Known Activations