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

    Neuronpedia

    INDEX
    Explanations

    personal reflections or statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of regret or reflection on past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.70
     (£
    -0.61
    Frag
    -0.60
    ·
    -0.60
    Char
    -0.59
     Kle
    -0.58
    Cor
    -0.58
    VG
    -0.57
    á
    -0.57
    Micro
    -0.57
    POSITIVE LOGITS
     also
    1.12
     furthermore
    1.01
     additionally
    0.99
     likewise
    0.89
     moreover
    0.89
    also
    0.87
     secondly
    0.83
     alternatively
    0.78
     similarly
    0.78
     ALSO
    0.77
    Act Density 0.795%

    No Known Activations