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

    Neuronpedia

    INDEX
    Explanations

    phrases related to location or events

    oai_token-act-pair · gpt-3.5-turbo

    specific names and titles related to locations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢİ
    -0.57
     âĢķ
    -0.57
     stronger
    -0.55
     —
    -0.53
     âĢİ
    -0.52
    fe
    -0.51
    0000000000000000
    -0.50
    ãĥīãĥ©ãĤ´ãĥ³
    -0.49
     ...
    -0.48
    cele
    -0.47
    POSITIVE LOGITS
    theless
    0.82
    intosh
    0.81
    etheless
    0.76
    anwhile
    0.75
    pite
    0.70
    uese
    0.67
    roma
    0.67
    culosis
    0.64
    foundland
    0.64
    MSN
    0.62
    Act Density 0.289%

    No Known Activations