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

    Neuronpedia

    INDEX
    Explanations

    names of famous people along with an action or description related to them

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate an action followed by specific subjects or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addons
    -0.63
    Eva
    -0.63
    Compat
    -0.61
     whence
    -0.61
    Materials
    -0.60
    AI
    -0.60
    LOD
    -0.59
     conver
    -0.59
    dogs
    -0.58
    Therefore
    -0.57
    POSITIVE LOGITS
     Jr
    0.87
    elaide
    0.87
    itone
    0.82
     QC
    0.80
     PhD
    0.80
     Sr
    0.79
    tsky
    0.75
    verett
    0.73
    SON
    0.71
     alias
    0.68
    Act Density 0.379%

    No Known Activations