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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with "It's"

    oai_token-act-pair · gpt-3.5-turbo

    introduction phrases or statements that capture attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranged
    -0.80
    existent
    -0.72
    result
    -0.69
     tert
    -0.63
     externalToEVAOnly
    -0.62
    options
    -0.62
    properties
    -0.61
    depend
    -0.59
     reject
    -0.59
     guiActiveUnfocused
    -0.59
    POSITIVE LOGITS
    advertisement
    0.92
    estern
    0.77
    htaking
    0.74
    loo
    0.67
     tempting
    0.67
    eva
    0.65
     sorcery
    0.65
     dawn
    0.63
     customary
    0.63
     ironic
    0.63
    Act Density 0.278%

    No Known Activations