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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consideration or concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions, limitations, or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tatt
    -0.70
    avorite
    -0.70
     Masquerade
    -0.70
     submar
    -0.69
     suspic
    -0.69
     Panc
    -0.68
     Sop
    -0.68
     Tale
    -0.66
     helicop
    -0.66
     paradise
    -0.64
    POSITIVE LOGITS
     regards
    0.82
    eous
    0.78
    ments
    0.75
    ardless
    0.73
    equality
    0.70
    ibility
    0.70
    ental
    0.70
    otaur
    0.69
    reon
    0.69
    leck
    0.68
    Act Density 0.032%

    No Known Activations