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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recent actions or creations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" and its variations, indicating possession or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fail
    -0.75
    apo
    -0.74
    abuse
    -0.72
     Cannot
    -0.71
     srfAttach
    -0.67
    itters
    -0.67
    eem
    -0.65
    ails
    -0.65
    lies
    -0.63
    Reading
    -0.62
    POSITIVE LOGITS
     begun
    1.37
     teamed
    1.35
     chosen
    1.27
     devised
    1.27
     created
    1.23
     been
    1.23
     assembled
    1.22
     partnered
    1.22
     gotten
    1.21
     collaborated
    1.18
    Act Density 0.278%

    No Known Activations