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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different phases or stages of a process

    oai_token-act-pair · gpt-3.5-turbo

    references to different phases or stages in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.88
    inately
    -0.83
    ILLE
    -0.81
     Rings
    -0.74
    esome
    -0.71
     Cosponsors
    -0.71
    byn
    -0.70
    llah
    -0.70
    ilial
    -0.70
    rious
    -0.69
    POSITIVE LOGITS
     phases
    0.93
     phase
    0.89
     stages
    0.86
    hift
    0.86
     transitions
    0.82
     Phase
    0.80
    ogue
    0.72
    tenance
    0.72
     stage
    0.71
    phase
    0.70
    Act Density 0.025%

    No Known Activations