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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong need or obligation

    oai_token-act-pair · gpt-3.5-turbo

    colloquial expressions emphasizing necessity or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thumbnails
    -0.82
    eering
    -0.69
    Reviewed
    -0.69
    worldly
    -0.67
    hips
    -0.66
    iated
    -0.66
    athing
    -0.65
    edly
    -0.65
    rors
    -0.65
    geist
    -0.65
    POSITIVE LOGITS
     gotta
    1.12
     nab
    0.82
     leave
    0.80
     give
    0.80
     listen
    0.79
     wanna
    0.78
     wait
    0.78
    terday
    0.77
     get
    0.74
     take
    0.74
    Act Density 0.008%

    No Known Activations