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

    Neuronpedia

    INDEX
    Explanations

    a particular adjective followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "growing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioned
    -0.80
    tta
    -0.76
    claimer
    -0.74
    pta
    -0.73
    osa
    -0.71
    oute
    -0.70
    ffe
    -0.70
    nee
    -0.70
    phis
    -0.69
    hiro
    -0.69
    POSITIVE LOGITS
     pains
    0.89
     subsequ
    0.77
     discontent
    0.76
     impat
    0.76
     realization
    0.72
     promot
    0.70
     homelessness
    0.70
    lass
    0.68
    nir
    0.68
     prospects
    0.67
    Act Density 0.033%

    No Known Activations