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

    Neuronpedia

    INDEX
    Explanations

    action verbs in progressive tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     representations
    -0.71
    ECD
    -0.67
     Preservation
    -0.63
     Monetary
    -0.63
     Responsibility
    -0.63
    attribute
    -0.62
    orthy
    -0.62
    saf
    -0.61
    DI
    -0.60
    soever
    -0.60
    POSITIVE LOGITS
     snowball
    1.50
     escalated
    1.33
     dwind
    1.33
     escalate
    1.25
     progressed
    1.25
     spir
    1.22
     progresses
    1.18
     escal
    1.16
     bloss
    1.15
     CONTIN
    1.13
    Act Density 0.557%

    No Known Activations