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

    Neuronpedia

    INDEX
    Explanations

    the superlative or ordinal form of words

    oai_token-act-pair · gpt-3.5-turbo

    indications of notable achievements or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presently
    -0.88
    INGTON
    -0.79
     Currently
    -0.75
     currently
    -0.70
    Currently
    -0.69
     hereby
    -0.68
    currently
    -0.67
    cgi
    -0.66
    ologies
    -0.65
    ony
    -0.65
    POSITIVE LOGITS
     catalyst
    1.20
     inspiration
    1.11
     impetus
    1.10
     instrumental
    1.05
     memorable
    1.02
     unsuccessful
    1.00
     standout
    0.98
     surprise
    0.97
     fateful
    0.97
     revelation
    0.93
    Act Density 0.298%

    No Known Activations