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

    Neuronpedia

    INDEX
    Explanations

    phrases related to participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to group affiliations or associations in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.78
     mete
    -0.72
     reckoning
    -0.72
     plotting
    -0.70
     committed
    -0.66
     stake
    -0.65
     brigade
    -0.65
    otes
    -0.65
     catapult
    -0.64
     adversaries
    -0.64
    POSITIVE LOGITS
    DM
    0.79
    Morning
    0.78
    heter
    0.75
    Monitor
    0.74
    gently
    0.73
    Quest
    0.71
    Japanese
    0.69
    itol
    0.68
    Park
    0.68
     Beir
    0.68
    Act Density 0.000%

    No Known Activations