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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public gatherings for a shared cause

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rallies or gathering actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.79
    etheless
    -0.78
    ©¶æ
    -0.76
    fiction
    -0.69
    ilic
    -0.66
    andro
    -0.64
    teness
    -0.63
    ijk
    -0.63
    ternity
    -0.63
    hid
    -0.62
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.87
     rallying
    0.80
    andise
    0.78
     chorus
    0.76
    steen
    0.75
    ivals
    0.72
    isers
    0.72
     rally
    0.70
     Rally
    0.70
     cries
    0.68
    Act Density 0.011%

    No Known Activations