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

    Neuronpedia

    INDEX
    Explanations

    social media names with a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'N' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.74
     breeze
    -0.71
     highs
    -0.69
     CLSID
    -0.68
     Cerberus
    -0.66
     swings
    -0.66
     Sparrow
    -0.65
     downed
    -0.65
     Photoshop
    -0.64
     horizont
    -0.63
    POSITIVE LOGITS
    uggets
    1.29
    erves
    1.10
    ominated
    1.08
    guyen
    1.07
    ucle
    1.07
    ihil
    1.05
    umerous
    1.04
    urse
    1.04
    aughty
    1.02
    ifty
    1.01
    Act Density 0.031%

    No Known Activations