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

    Neuronpedia

    INDEX
    Explanations

    words related to breaks or pauses

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to recurring themes or categories, particularly regarding legislative and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peninsula
    -0.71
     damn
    -0.66
     dear
    -0.65
    izoph
    -0.63
    agine
    -0.63
     laundering
    -0.62
    ETHOD
    -0.58
    Äĩ
    -0.58
     thirds
    -0.58
     awake
    -0.58
    POSITIVE LOGITS
    es
    2.38
    ively
    1.20
    esville
    1.15
    esian
    1.13
    ed
    1.11
    ions
    1.11
    esy
    1.07
    ername
    1.07
    engers
    1.04
    icals
    1.03
    Act Density 0.087%

    No Known Activations