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

    Neuronpedia

    INDEX
    Explanations

    numbers that have a hyphen before them

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical sentiments expressed in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nce
    -0.81
    nces
    -0.77
     Invisible
    -0.68
    iazep
    -0.67
     Hels
    -0.65
    \\\\\\\\
    -0.65
     Bees
    -0.64
     Perse
    -0.63
    ippi
    -0.62
     perm
    -0.62
    POSITIVE LOGITS
    interstitial
    0.90
    based
    0.85
    style
    0.79
    related
    0.78
    intensive
    0.78
    eligible
    0.77
    walking
    0.77
    derived
    0.76
    general
    0.75
    breaker
    0.75
    Act Density 0.122%

    No Known Activations