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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating agreement or collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bluff
    -0.64
     consolidation
    -0.61
     flats
    -0.58
     playback
    -0.58
     Survivors
    -0.58
     compression
    -0.58
     Virus
    -0.58
     Transformation
    -0.57
    elsen
    -0.57
    sterdam
    -0.57
    POSITIVE LOGITS
    Ïī
    0.78
     sidx
    0.75
    itten
    0.71
    speaking
    0.71
    apon
    0.67
    enged
    0.67
    enge
    0.65
    agher
    0.65
    interested
    0.64
    achable
    0.64
    Act Density 0.365%

    No Known Activations