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

    Neuronpedia

    INDEX
    Explanations

    specific verbs related to carrying out or enforcing actions

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs indicating states, actions, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NCT
    -0.77
    selves
    -0.74
     Finance
    -0.71
    etheless
    -0.70
     deviation
    -0.65
     Heritage
    -0.64
     Price
    -0.63
     Fighters
    -0.63
     apologies
    -0.61
     Accountability
    -0.61
    POSITIVE LOGITS
    aps
    1.02
    oop
    0.93
    oxic
    0.91
    chery
    0.90
    odic
    0.90
    apon
    0.89
    rug
    0.85
    oval
    0.85
    oused
    0.85
    anium
    0.84
    Act Density 0.137%

    No Known Activations