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 a previous state or place

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to "the" followed by various topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.73
    merce
    -0.71
    roximately
    -0.66
    urst
    -0.63
    ado
    -0.63
    Spread
    -0.63
    ados
    -0.63
    zai
    -0.62
    ghai
    -0.62
    acebook
    -0.62
    POSITIVE LOGITS
     whence
    0.83
     fray
    0.82
     fold
    0.81
     basics
    0.79
     haunt
    0.74
     drawing
    0.72
     adolesc
    0.69
     original
    0.68
     plur
    0.66
     classroom
    0.64
    Act Density 0.175%

    No Known Activations