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

    Neuronpedia

    INDEX
    Explanations

    references to pet characteristics and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sphere
    -0.16
    Tweet
    -0.15
    _ble
    -0.14
    nett
    -0.14
    -----------*/↵
    -0.14
     пÑĢоз
    -0.14
     Ness
    -0.14
     ÏĢε
    -0.14
    _fh
    -0.14
    Sphere
    -0.13
    POSITIVE LOGITS
     foster
    0.18
     neut
    0.18
     reactive
    0.17
     Labs
    0.17
    ossier
    0.17
     gentle
    0.17
     crate
    0.17
    gent
    0.16
     gentleman
    0.16
    idal
    0.15
    Act Density 0.024%

    No Known Activations