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

    Neuronpedia

    INDEX
    Explanations

    terms related to disruption and disturbances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haul
    -0.17
    erv
    -0.15
    ows
    -0.15
    ervo
    -0.15
    gie
    -0.15
    borg
    -0.14
    รà¸Ķ
    -0.14
    ettle
    -0.14
    bian
    -0.14
     republika
    -0.14
    POSITIVE LOGITS
    /dist
    0.22
     Interrupt
    0.19
    ive
    0.19
    ively
    0.19
    /conf
    0.18
     INTERRUPTION
    0.16
    /dis
    0.16
     interrupt
    0.16
     INTERRU
    0.16
     disrupt
    0.15
    Act Density 0.036%

    No Known Activations