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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating positive or negative qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.79
    DERR
    -0.70
    _>
    -0.69
    onics
    -0.69
    FAULT
    -0.66
     Burnett
    -0.64
     srfAttach
    -0.64
     Clouds
    -0.62
    ysics
    -0.61
    Doctors
    -0.61
    POSITIVE LOGITS
     piece
    0.69
    worldly
    0.67
    stros
    0.67
     beast
    0.66
     milestone
    0.66
     foray
    0.65
    ranch
    0.64
    sided
    0.64
     gap
    0.63
     initiative
    0.63
    Act Density 0.229%

    No Known Activations