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

    Neuronpedia

    INDEX
    Explanations

    words related to shelter or protection, particularly related to animals

    oai_token-act-pair · gpt-3.5-turbo

    references to nesting or homes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERSION
    -0.79
    Primary
    -0.75
    ãĥĨãĤ£
    -0.73
     muscular
    -0.69
    BILITY
    -0.67
    vation
    -0.67
     physical
    -0.66
    WAYS
    -0.65
    physical
    -0.63
    OTO
    -0.62
    POSITIVE LOGITS
     nest
    1.05
    lace
    1.02
    acle
    0.95
     nests
    0.95
    eers
    0.90
    arus
    0.88
    lings
    0.86
    lund
    0.81
    thal
    0.81
    eer
    0.78
    Act Density 0.005%

    No Known Activations