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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction and causing harm

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "destroy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flu
    -0.69
    isp
    -0.66
     MLA
    -0.65
     Johns
    -0.64
    oft
    -0.63
    voc
    -0.63
     Pace
    -0.63
    vo
    -0.62
    ¶
    -0.61
    Community
    -0.61
    POSITIVE LOGITS
     destroy
    3.31
    destroy
    2.53
     Destroy
    2.32
    Destroy
    2.16
     destroying
    2.10
     destroys
    2.03
     destroyer
    2.00
     destroyed
    1.90
     destruction
    1.84
     kill
    1.55
    Act Density 0.014%

    No Known Activations