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

    Neuronpedia

    INDEX
    Explanations

    words related to referring or alluding to something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to something being mentioned or pointed out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rils
    -0.73
    iste
    -0.72
    -|
    -0.69
    alysis
    -0.68
    Login
    -0.68
    HC
    -0.67
    trace
    -0.67
    abouts
    -0.67
    mask
    -0.66
    isphere
    -0.66
    POSITIVE LOGITS
     plural
    0.71
     situations
    0.70
     those
    0.70
     the
    0.69
     incidents
    0.67
     phrases
    0.64
     earlier
    0.63
     terminology
    0.62
     initials
    0.62
     pronunciation
    0.61
    Act Density 0.059%

    No Known Activations