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

    Neuronpedia

    INDEX
    Explanations

    statements about the current state or progress of various situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the state of affairs or current conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [+]
    -0.71
     (>
    -0.66
    emark
    -0.65
     Tens
    -0.65
    pora
    -0.64
    odied
    -0.63
    affe
    -0.63
    ewitness
    -0.63
    raint
    -0.63
    ¿½
    -0.62
    POSITIVE LOGITS
     alright
    0.91
    icably
    0.89
     downhill
    0.87
     differently
    0.85
     fine
    0.84
     hun
    0.82
     ok
    0.81
     OK
    0.78
     sorted
    0.77
     okay
    0.77
    Act Density 0.134%

    No Known Activations