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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating timing or something happening at an early stage

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating timing or occurrence in the near future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.77
    inen
    -0.72
    eker
    -0.71
    yne
    -0.71
    ifferent
    -0.69
    phabet
    -0.69
    ainer
    -0.68
    ictive
    -0.68
    icative
    -0.67
    ication
    -0.67
    POSITIVE LOGITS
     possible
    0.85
     practicable
    0.83
     Fiji
    0.72
     Persia
    0.67
     dusk
    0.66
     1954
    0.64
     Noon
    0.63
     Possible
    0.62
     Tunisia
    0.62
     Johannes
    0.62
    Act Density 0.033%

    No Known Activations