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

    Neuronpedia

    INDEX
    Explanations

    terms related to collaboration and projects

    oai_token-act-pair · gpt-3.5-turbo

    collaborative projects and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibling
    -0.63
    caster
    -0.60
    eness
    -0.59
    uck
    -0.59
    itus
    -0.58
    aunt
    -0.55
    fighters
    -0.55
    isky
    -0.53
    ergus
    -0.53
    acus
    -0.53
    POSITIVE LOGITS
     manner
    0.72
     quantities
    0.61
     premises
    0.60
     prelim
    0.60
     basis
    0.58
     entirety
    0.57
     arsen
    0.57
     afore
    0.56
     Calder
    0.54
     accordance
    0.52
    Act Density 1.204%

    No Known Activations