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

    Neuronpedia

    INDEX
    Explanations

    words related to continuity or extension

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cont" indicating continuity or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.84
    EStream
    -0.76
    BSD
    -0.76
    Pear
    -0.75
     Wolves
    -0.75
    ħĭ
    -0.71
     Sunshine
    -0.69
     Redemption
    -0.69
     Rath
    -0.67
    MQ
    -0.66
    POSITIVE LOGITS
    oso
    0.95
    ented
    0.94
    rast
    0.93
    ours
    0.91
    ortion
    0.87
    rived
    0.86
    ributes
    0.84
    oured
    0.83
    ents
    0.83
    itives
    0.82
    Act Density 0.007%

    No Known Activations