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

    Neuronpedia

    INDEX
    Explanations

    phrases describing firmness or stability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating stability or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emin
    -0.94
    ammy
    -0.78
    nesota
    -0.77
    ifax
    -0.75
    vernment
    -0.73
    igraph
    -0.71
    xual
    -0.70
    ery
    -0.68
    ĸļ
    -0.68
    udi
    -0.65
    POSITIVE LOGITS
     entrenched
    1.02
     rooted
    0.95
     footing
    0.91
     firmly
    0.85
     adherent
    0.85
     believer
    0.83
     ens
    0.81
     foothold
    0.81
     anchored
    0.80
    lishes
    0.80
    Act Density 0.065%

    No Known Activations