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

    Neuronpedia

    INDEX
    Explanations

    names that contain the sequence "amm"

    oai_token-act-pair · gpt-3.5-turbo

    words related to mammals or specific terms associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Intent
    -0.69
    ween
    -0.66
    grade
    -0.66
    nces
    -0.65
    voy
    -0.64
     tilt
    -0.61
    choes
    -0.61
    take
    -0.59
    PDATE
    -0.58
    yip
    -0.57
    POSITIVE LOGITS
    olit
    1.13
    arella
    0.99
    oths
    0.97
    obil
    0.97
    obile
    0.94
    agic
    0.90
    ateur
    0.89
    erville
    0.88
    igrants
    0.88
    ush
    0.88
    Act Density 0.014%

    No Known Activations