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

    Neuronpedia

    INDEX
    Explanations

    references to interruptions or disturbances in a narrative

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

    interruption or interference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vů
    -0.44
    mybatisplus
    -0.43
    Citiți
    -0.43
     GenerationType
    -0.41
     Signalez
    -0.40
    AndEndTag
    -0.38
    ftagPool
    -0.38
    Literatur
    -0.38
    ssf
    -0.38
    RenderAtEndOf
    -0.37
    POSITIVE LOGITS
     interruptions
    0.76
     interrupts
    0.72
     interrupting
    0.69
     interruption
    0.68
     interrupted
    0.63
     interrupt
    0.62
     interrump
    0.61
    interrupt
    0.60
     interrup
    0.60
    interrupted
    0.58
    Act Density 0.098%

    No Known Activations