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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating communication or interaction

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional or dramatic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bleacher
    -0.65
    aughtered
    -0.64
    htaking
    -0.61
    osate
    -0.61
    Äį
    -0.59
    oola
    -0.58
     guiActiveUn
    -0.57
    arnaev
    -0.57
    iov
    -0.56
    uterte
    -0.56
    POSITIVE LOGITS
     theirs
    0.72
     them
    0.67
     hers
    0.61
     latter
    0.60
     afterward
    0.55
    +.
    0.55
    Interstitial
    0.53
    ģ«
    0.53
    Otherwise
    0.52
     anyway
    0.51
    Act Density 1.510%

    No Known Activations