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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions, activities, and tasks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dissatisfaction or needs related to resources or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.76
    enegger
    -0.68
    abus
    -0.67
    Naz
    -0.65
    lich
    -0.65
    ileaks
    -0.64
    Merit
    -0.64
    xon
    -0.63
    justice
    -0.63
    Pitt
    -0.63
    POSITIVE LOGITS
     their
    1.22
     themselves
    1.18
    their
    1.03
     theirs
    1.01
     THEIR
    0.91
     varying
    0.90
     Their
    0.86
     unrealistic
    0.86
     shortcuts
    0.85
     these
    0.84
    Act Density 0.547%

    No Known Activations