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

    Neuronpedia

    INDEX
    Explanations

    numerical changes or trends

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes in numerical data, particularly increases and decreases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vault
    -0.57
     restruct
    -0.54
    ciating
    -0.53
     briefings
    -0.52
     subtitles
    -0.52
    ATA
    -0.51
     scrut
    -0.51
     Blink
    -0.50
    got
    -0.49
     apartheid
    -0.48
    POSITIVE LOGITS
     in
    0.97
    xual
    0.88
    pour
    0.87
    luster
    0.83
    over
    0.81
    lust
    0.79
     rate
    0.77
     of
    0.74
     therein
    0.73
     towards
    0.73
    Act Density 0.160%

    No Known Activations