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

    Neuronpedia

    INDEX
    Explanations

    words related to achieving success or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of traction or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peninsula
    -0.74
    ospital
    -0.71
    thus
    -0.70
    tein
    -0.66
    ulk
    -0.65
    rug
    -0.65
    nance
    -0.62
    yan
    -0.62
     Thanksgiving
    -0.62
     Birthday
    -0.61
    POSITIVE LOGITS
     traction
    1.02
    ãĥ¼ãĥĨ
    0.82
    ability
    0.79
    ãĤ¤ãĥĪ
    0.77
    wagon
    0.76
    onomy
    0.74
    itious
    0.73
    irtual
    0.71
    vine
    0.69
    culosis
    0.69
    Act Density 0.008%

    No Known Activations