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

    Neuronpedia

    INDEX
    Explanations

    words related to pride or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing pride and significant accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+-+
    -0.82
    ntil
    -0.80
    ndra
    -0.73
    lished
    -0.66
    Ü
    -0.66
    tions
    -0.65
    vertisement
    -0.65
     Doodle
    -0.64
    bably
    -0.63
    IOR
    -0.62
    POSITIVE LOGITS
     liberties
    1.14
     precautions
    1.12
     aback
    1.04
     steps
    1.02
     cues
    1.01
    advant
    1.00
     risks
    0.99
     seriously
    0.98
     shortcuts
    0.98
     oath
    0.98
    Act Density 0.192%

    No Known Activations