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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing preferences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation or positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MRI
    -0.82
    strate
    -0.81
    elaide
    -0.81
    owned
    -0.78
    cum
    -0.76
    udder
    -0.75
    herer
    -0.75
    perse
    -0.74
    arate
    -0.73
    strap
    -0.70
    POSITIVE LOGITS
     idea
    1.22
     outcome
    1.14
     entirety
    1.09
     possibility
    1.09
     notion
    1.07
     latter
    1.06
     same
    1.02
     plight
    0.99
     slightest
    0.99
     sheer
    0.98
    Act Density 0.377%

    No Known Activations