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

    Neuronpedia

    INDEX
    Explanations

    words related to anxiety and concern

    oai_token-act-pair · gpt-3.5-turbo

    words related to anxiety and notable cultural artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OST
    -0.71
     Lamp
    -0.67
     Primordial
    -0.61
     Dragonbound
    -0.61
     Codec
    -0.61
     onwards
    -0.60
     sting
    -0.60
     Enhanced
    -0.60
     FISA
    -0.59
     trap
    -0.59
    POSITIVE LOGITS
    iences
    1.13
    itability
    0.98
    itable
    0.96
    ieties
    0.95
    kes
    0.95
    voc
    0.95
    pless
    0.94
    bly
    0.91
    itors
    0.90
    cler
    0.89
    Act Density 0.049%

    No Known Activations