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

    Neuronpedia

    INDEX
    Explanations

    words related to aggression and obsession

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggression and compulsive behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deposition
    -0.67
    quartered
    -0.67
    LEASE
    -0.62
     allowance
    -0.61
     oath
    -0.60
     Citizens
    -0.60
    ulic
    -0.57
     Amendment
    -0.57
     accompanying
    -0.56
     confidentiality
    -0.56
    POSITIVE LOGITS
    ions
    1.39
    ors
    1.35
    ively
    1.27
    ional
    1.21
    iveness
    1.15
    ority
    1.12
    or
    1.04
    ours
    1.00
    uations
    0.98
    ures
    0.97
    Act Density 0.034%

    No Known Activations