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

    Neuronpedia

    INDEX
    Explanations

    phrases related to going back in time or returning to previous situations

    oai_token-act-pair · gpt-3.5-turbo

    references to places or states of being that individuals or groups return to

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urst
    -0.78
    bsp
    -0.68
    ander
    -0.66
    ilers
    -0.66
    orsi
    -0.66
    illion
    -0.65
    oS
    -0.64
    each
    -0.62
    frey
    -0.62
    pton
    -0.62
    POSITIVE LOGITS
     fold
    1.05
     basics
    1.01
     original
    0.98
     roots
    0.96
     originals
    0.89
     old
    0.82
     rightful
    0.81
     whence
    0.81
     fray
    0.81
     glory
    0.80
    Act Density 0.224%

    No Known Activations