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

    Neuronpedia

    INDEX
    Explanations

    references to lengthy past events or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.76
    utterstock
    -0.76
    amina
    -0.72
    ando
    -0.72
    agers
    -0.72
    agraph
    -0.70
    ateurs
    -0.69
    emouth
    -0.69
    iffs
    -0.69
    hap
    -0.68
    POSITIVE LOGITS
     precedent
    0.76
     record
    0.76
     history
    0.74
     dating
    0.71
     revolving
    0.66
     stretching
    0.66
     ingrained
    0.66
     nem
    0.65
    links
    0.65
     intertwined
    0.65
    Act Density 0.041%

    No Known Activations