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

    Neuronpedia

    INDEX
    Explanations

    references to protective or security-related roles and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Animalia
    -0.16
    izar
    -0.15
    ickerView
    -0.15
    ambre
    -0.15
    ucher
    -0.15
    izando
    -0.14
    /*č↵
    -0.14
    andra
    -0.14
    orris
    -0.14
     agre
    -0.14
    POSITIVE LOGITS
    aver
    0.15
     Benton
    0.14
    ipo
    0.14
    t
    0.14
     Bent
    0.14
    ingroup
    0.14
     Lamp
    0.14
    rail
    0.14
    affles
    0.14
     Sez
    0.14
    Act Density 0.018%

    No Known Activations