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

    Neuronpedia

    INDEX
    Explanations

    instances of physical confrontations or altercations between people

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to individuals involved in various actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.87
    ãĥ£
    -0.66
    orie
    -0.65
     ILCS
    -0.65
    BN
    -0.64
    apter
    -0.62
    lance
    -0.62
    votes
    -0.61
    ilib
    -0.60
    np
    -0.59
    POSITIVE LOGITS
     senseless
    1.01
     harshly
    0.87
     merciless
    0.86
     orally
    0.82
     violently
    0.81
     verbally
    0.81
     unconscious
    0.80
     relentlessly
    0.78
     inappropriately
    0.78
     undermin
    0.78
    Act Density 0.164%

    No Known Activations