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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    numerical or time-based data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FW
    -0.85
     PF
    -0.79
     Jem
    -0.77
     CES
    -0.74
     RTX
    -0.74
     NF
    -0.73
     Bang
    -0.73
     Cue
    -0.72
     RF
    -0.70
     mixed
    -0.70
    POSITIVE LOGITS
    41
    1.66
    56
    1.64
    58
    1.63
    28
    1.63
    48
    1.62
    46
    1.62
    36
    1.62
    42
    1.62
    54
    1.61
    72
    1.60
    Act Density 0.116%

    No Known Activations