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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aber
    -0.67
    Els
    -0.67
    ãĥij
    -0.65
    sites
    -0.63
    Reviewer
    -0.62
    nox
    -0.61
    history
    -0.61
    ENCE
    -0.61
     overriding
    -0.60
    Luck
    -0.60
    POSITIVE LOGITS
     prepares
    1.19
     approached
    1.16
     exited
    1.06
     awaited
    1.06
     toured
    1.05
     unfolded
    1.04
     transitioned
    1.04
     waited
    1.04
     walked
    1.01
     paced
    0.99
    Act Density 0.096%

    No Known Activations