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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "praise" or "praiseworthy"

    oai_token-act-pair · gpt-3.5-turbo

    words related to praise and positive recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.88
    ding
    -0.79
    lies
    -0.78
    lings
    -0.76
    flies
    -0.75
    owship
    -0.73
    nets
    -0.73
    glers
    -0.73
    hips
    -0.72
    worms
    -0.69
    POSITIVE LOGITS
    irie
    1.08
    iries
    0.85
    umatic
    0.80
     Autumn
    0.74
    jit
    0.72
    ignty
    0.72
    kt
    0.71
    pload
    0.71
    ĺħ
    0.71
    zza
    0.70
    Act Density 0.029%

    No Known Activations