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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating surprising or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.95
    azines
    -0.72
    omever
    -0.71
    azine
    -0.70
    onents
    -0.69
    alions
    -0.66
    omorph
    -0.65
    ophers
    -0.64
     buttons
    -0.62
    û
    -0.62
    POSITIVE LOGITS
     reversal
    1.00
     effort
    0.88
     nutshell
    0.88
     bombshell
    0.87
     bid
    0.86
     concession
    0.84
     attempt
    0.80
    stakes
    0.80
     testament
    0.79
    Synopsis
    0.78
    Act Density 0.224%

    No Known Activations