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

    Neuronpedia

    INDEX
    Explanations

    the word "monolog" or similar variations with different levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    words related to various fields of study, particularly focusing on aspects of "logic" and "analogies."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plan
    -0.63
    noon
    -0.62
     uncond
    -0.60
    words
    -0.60
     EAR
    -0.60
    eff
    -0.59
    FACE
    -0.58
    FUL
    -0.58
    affe
    -0.58
    kins
    -0.57
    POSITIVE LOGITS
    ues
    1.78
    raphic
    1.24
    uing
    1.20
    raph
    1.18
    rams
    1.16
    ued
    1.16
    ous
    1.10
    etics
    1.07
    ical
    1.06
    etic
    1.06
    Act Density 0.104%

    No Known Activations