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

    Neuronpedia

    INDEX
    Explanations

    subjective statements or opinions paired with a corresponding verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    livious
    -0.75
    ORK
    -0.72
    zar
    -0.69
    vati
    -0.69
     Siren
    -0.68
    és
    -0.67
    ahime
    -0.66
    edia
    -0.65
     Debor
    -0.64
    ALLY
    -0.64
    POSITIVE LOGITS
     whatsoever
    0.85
     deems
    0.78
    pires
    0.77
    aign
    0.73
     imaginable
    0.72
     wishes
    0.70
     deem
    0.70
     occasion
    0.69
    ppings
    0.68
    ifice
    0.68
    Act Density 0.145%

    No Known Activations