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

    Neuronpedia

    INDEX
    Explanations

    official websites and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to official sites or announcements related to various entities or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.79
    etheless
    -0.72
    ancial
    -0.71
     whichever
    -0.69
     bragging
    -0.68
     respectively
    -0.67
     margins
    -0.67
     ourselves
    -0.65
     shaming
    -0.64
     justifying
    -0.64
    POSITIVE LOGITS
    lvl
    0.85
    Jr
    0.82
     ???
    0.75
     LV
    0.73
     TBD
    0.73
     lvl
    0.71
    Lv
    0.71
     Jr
    0.70
     ..............
    0.69
    à¦
    0.68
    Act Density 0.183%

    No Known Activations