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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful and destructive actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to destruction or breaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghan
    -0.74
    agonist
    -0.70
    umeric
    -0.70
    ogo
    -0.69
    uana
    -0.69
    abet
    -0.67
    pmwiki
    -0.67
    adh
    -0.66
    annis
    -0.66
    aning
    -0.65
    POSITIVE LOGITS
     shatter
    0.86
     shattering
    0.86
     smashed
    0.85
     shards
    0.82
     shattered
    0.80
    dragon
    0.73
    ãĥ¼ãĥ«
    0.70
     ribs
    0.68
     skulls
    0.68
     wed
    0.67
    Act Density 0.025%

    No Known Activations