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

    Neuronpedia

    INDEX
    Explanations

    expressions or clauses indicating a contrast or an addition to a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the phrase "after all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alysed
    -0.74
    MpServer
    -0.74
    SN
    -0.69
    pec
    -0.68
    Near
    -0.67
    Alias
    -0.60
    xon
    -0.59
    Repeat
    -0.59
    min
    -0.58
     vari
    -0.57
    POSITIVE LOGITS
     why
    0.82
    nob
    0.78
     nobody
    0.75
     there
    0.74
     imagine
    0.73
     wouldn
    0.71
    tons
    0.71
     unlike
    0.71
     isn
    0.70
     suppose
    0.70
    Act Density 0.099%

    No Known Activations