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

    Neuronpedia

    INDEX
    Explanations

    references to taking concrete actions or steps

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Lego, money, and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.90
    ntil
    -0.89
    ailability
    -0.83
    ambo
    -0.77
    ategories
    -0.73
    -+-+
    -0.72
    etheless
    -0.70
    athy
    -0.68
    vertisement
    -0.66
    tions
    -0.65
    POSITIVE LOGITS
     seriously
    0.96
     aback
    0.92
     away
    0.85
     plunge
    0.85
     reins
    0.83
     lightly
    0.82
     liberties
    0.81
     Seriously
    0.81
     virginity
    0.80
     cues
    0.80
    Act Density 0.234%

    No Known Activations