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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or significance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evidence
    -0.79
    Enter
    -0.72
    Edit
    -0.71
    Autom
    -0.66
    Sources
    -0.65
    ographs
    -0.64
    immigration
    -0.64
     EVs
    -0.64
    laim
    -0.63
     annually
    -0.63
    POSITIVE LOGITS
     lot
    1.49
     bunch
    1.32
     couple
    1.21
     LOT
    1.11
     bit
    1.09
     few
    1.09
     nice
    1.09
     little
    1.06
     guy
    0.98
     handful
    0.97
    Act Density 0.694%

    No Known Activations