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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a requirement or consequence

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements that imply necessity or prerequisites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     curs
    -0.59
    kins
    -0.59
    lap
    -0.58
     blows
    -0.57
     irony
    -0.56
    utenberg
    -0.55
     neat
    -0.55
    unin
    -0.55
    CG
    -0.54
     enlight
    -0.53
    POSITIVE LOGITS
     intend
    0.75
     aspire
    0.75
     planning
    0.73
     contemplating
    0.73
    soever
    0.71
     embark
    0.69
    aping
    0.69
     intends
    0.68
    utical
    0.68
     aspiring
    0.67
    Act Density 0.202%

    No Known Activations