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

    Neuronpedia

    INDEX
    Explanations

    words associated with behavior and behavioral change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laurens
    -0.74
    MILLIS
    -0.65
     Milne
    -0.65
     Clooney
    -0.63
     Tup
    -0.62
    rafted
    -0.62
     gzip
    -0.61
     Fitz
    -0.60
     Fitzpatrick
    -0.60
     Nip
    -0.60
    POSITIVE LOGITS
     behavior
    2.23
     behaviour
    2.11
     Behavior
    2.06
    behavior
    2.00
     BEHAVIOR
    1.93
    Behavior
    1.92
     behaviors
    1.91
     Behaviour
    1.88
     behaviours
    1.81
    behaviour
    1.81
    Act Density 0.071%

    No Known Activations