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

    Neuronpedia

    INDEX
    Explanations

    words related to gratitude and appreciation

    oai_token-act-pair · gpt-3.5-turbo

    words related to appreciation and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bermuda
    -0.70
     Cthulhu
    -0.70
     Span
    -0.70
     purse
    -0.70
     haz
    -0.65
     Somerset
    -0.65
     Devils
    -0.64
     Warner
    -0.64
     boarding
    -0.64
     Gamergate
    -0.63
    POSITIVE LOGITS
    reci
    1.37
    ocity
    1.02
    ate
    0.91
    ated
    0.90
    uries
    0.90
    bled
    0.89
    ating
    0.89
     recip
    0.87
    issance
    0.87
    atable
    0.86
    Act Density 0.006%

    No Known Activations