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

    Neuronpedia

    INDEX
    Explanations

    terms related to disturbance and disruption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haul
    -0.19
    borg
    -0.17
    ervo
    -0.15
    lake
    -0.15
    CU
    -0.15
    kits
    -0.15
    respuesta
    -0.14
    aret
    -0.14
    gie
    -0.14
    itate
    -0.14
    POSITIVE LOGITS
    /dist
    0.26
    /conf
    0.23
    ingly
    0.19
     Tactics
    0.18
    /error
    0.18
     caused
    0.16
    ive
    0.16
    /errors
    0.16
    644
    0.15
    ulence
    0.15
    Act Density 0.107%

    No Known Activations