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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or summarization

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the idea of being fundamental or foundational to a concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ey
    -0.75
    ng
    -0.70
     Giant
    -0.68
    rer
    -0.67
     palms
    -0.67
    seller
    -0.66
     Ced
    -0.62
    ttp
    -0.62
    ador
    -0.61
    river
    -0.59
    POSITIVE LOGITS
    yrinth
    0.83
     unchanged
    0.81
    etheless
    0.80
    phabet
    0.79
     guiActiveUn
    0.79
     unemploy
    0.77
     unint
    0.77
    qqa
    0.76
     metic
    0.75
     indistinguishable
    0.75
    Act Density 0.007%

    No Known Activations