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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical injuries or wound care

    oai_token-act-pair · gpt-3.5-turbo

    terms related to barriers and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prime
    -0.83
    onso
    -0.73
    medi
    -0.70
    ettel
    -0.67
    paces
    -0.65
    infeld
    -0.65
     PLUS
    -0.65
     tremend
    -0.64
    educ
    -0.64
    jen
    -0.64
    POSITIVE LOGITS
     arsen
    0.64
     coats
    0.61
     clouds
    0.61
     clad
    0.61
     caut
    0.60
     hides
    0.60
    Footnote
    0.60
    bons
    0.58
     adorned
    0.58
     Clouds
    0.58
    Act Density 0.145%

    No Known Activations