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

    Neuronpedia

    INDEX
    Explanations

    specific numbers or codes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 70 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yang
    -0.79
    uler
    -0.75
    vern
    -0.70
    hold
    -0.68
    vol
    -0.67
    clud
    -0.67
    ellation
    -0.65
    urer
    -0.65
    plom
    -0.64
     sacr
    -0.63
    POSITIVE LOGITS
     ILCS
    1.31
    70
    0.96
    80
    0.90
    mph
    0.87
    CTV
    0.87
     GHz
    0.84
    40
    0.83
    75
    0.82
    81
    0.80
    69
    0.79
    Act Density 0.035%

    No Known Activations