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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction or damaging actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elier
    -0.16
    ford
    -0.16
    sez
    -0.16
    backs
    -0.15
    atics
    -0.15
    /out
    -0.15
    ji
    -0.15
    ForResult
    -0.15
    gesi
    -0.14
    stral
    -0.14
    POSITIVE LOGITS
     havoc
    0.19
    ively
    0.17
    swer
    0.16
    lijk
    0.16
    iveness
    0.16
    æİī
    0.15
    urgeon
    0.15
    à¥įण
    0.15
    ive
    0.15
    edException
    0.15
    Act Density 0.041%

    No Known Activations