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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.71
    âĶĢâĶĢ
    -0.59
    terday
    -0.54
     CPC
    -0.52
    ãĥŁ
    -0.52
    theless
    -0.52
    acebook
    -0.52
     Fancy
    -0.51
     Italians
    -0.51
    etheless
    -0.51
    POSITIVE LOGITS
    zinski
    0.82
    erman
    0.77
    ansky
    0.76
    gaard
    0.76
    linger
    0.74
    lett
    0.74
    antz
    0.73
    ley
    0.73
    inski
    0.71
    burn
    0.71
    Act Density 0.276%

    No Known Activations