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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values within a range

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to age demographics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooters
    -0.55
    Variable
    -0.54
    ailability
    -0.53
     behavi
    -0.53
    illery
    -0.53
    edIn
    -0.51
     notor
    -0.51
     Trog
    -0.50
     conduc
    -0.50
    errors
    -0.49
    POSITIVE LOGITS
     thru
    1.18
    -$
    1.17
     onwards
    1.16
    –
    1.15
    %-
    1.14
     through
    1.07
     onward
    1.02
     to
    0.99
    âĢij
    0.92
     till
    0.91
    Act Density 0.356%

    No Known Activations