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

    Neuronpedia

    INDEX
    Explanations

    references to actions or events happening at the last minute

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing critical or late timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bir
    -0.90
    Hor
    -0.73
     Bir
    -0.70
     Controls
    -0.67
    Gy
    -0.65
    origin
    -0.64
     Traps
    -0.63
     Starter
    -0.63
    venants
    -0.63
     resumes
    -0.62
    POSITIVE LOGITS
    imester
    0.90
    fm
    0.88
    ebin
    0.83
    cation
    0.74
    asio
    0.72
    etime
    0.71
    ieri
    0.71
     penn
    0.71
     voic
    0.70
    iscal
    0.69
    Act Density 0.052%

    No Known Activations