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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and events

    oai_token-act-pair · gpt-3.5-turbo

    references to events or activities related to community gatherings and public interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.70
     predec
    -0.65
     advoc
    -0.60
     corrid
    -0.56
     millisec
    -0.54
     nonex
    -0.51
    ificant
    -0.51
     antid
    -0.51
    afer
    -0.50
    ãĥ¼ãĥĨãĤ£
    -0.50
    POSITIVE LOGITS
    )?
    0.90
    !!!!
    0.76
    ?
    0.76
    )!
    0.74
    !).
    0.73
    !?
    0.73
     Quote
    0.72
    !
    0.71
    "?
    0.71
    ¶
    0.70
    Act Density 0.691%

    No Known Activations