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

    Neuronpedia

    INDEX
    Explanations

    information related to news and current events

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and estimates related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whilst
    -0.71
     welf
    -0.62
     tremend
    -0.62
     splend
    -0.61
    colour
    -0.60
    cult
    -0.59
     Grimoire
    -0.59
    à¨
    -0.58
    cellence
    -0.58
    Firstly
    -0.57
    POSITIVE LOGITS
     meanwhile
    1.02
     afterward
    0.91
     however
    0.90
     later
    0.83
     declined
    0.78
     spokeswoman
    0.77
     also
    0.76
     reportedly
    0.74
     spokesman
    0.73
     meantime
    0.72
    Act Density 1.531%

    No Known Activations