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

    Neuronpedia

    INDEX
    Explanations

    mentions of tutoring or being tutored

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.92
    cale
    -0.71
     gulf
    -0.66
    ¯¯
    -0.62
    ilitary
    -0.61
     saline
    -0.60
     Peninsula
    -0.60
    UNCH
    -0.59
     acute
    -0.59
     Sins
    -0.59
    POSITIVE LOGITS
    tle
    1.32
    ility
    1.15
    ilities
    1.11
    ting
    1.05
    opia
    1.04
    glers
    1.04
    te
    1.04
    hered
    1.02
    cher
    1.01
    ierrez
    1.01
    Act Density 0.029%

    No Known Activations