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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explaining reasons or causes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "part of" and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rams
    -0.82
    ares
    -0.73
    eches
    -0.68
    onet
    -0.67
    orks
    -0.66
    ynes
    -0.65
    oons
    -0.64
     newsletters
    -0.64
    eder
    -0.63
    ICES
    -0.63
    POSITIVE LOGITS
     reason
    1.24
     reasoning
    0.90
     impetus
    0.89
     why
    0.89
     explanation
    0.88
     motivation
    0.87
     reasons
    0.84
     blame
    0.82
    Reason
    0.78
     frustration
    0.77
    Act Density 0.090%

    No Known Activations