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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making or selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myself
    -0.16
    IFY
    -0.15
     XmlDocument
    -0.15
    ADR
    -0.14
    ely
    -0.14
     Turk
    -0.14
    urgery
    -0.14
     armor
    -0.14
    430
    -0.13
    aret
    -0.13
    POSITIVE LOGITS
     Frid
    0.16
    emoc
    0.15
     Birthday
    0.15
    shint
    0.15
    <source
    0.15
    ãĥ¯ãĥ¼
    0.15
    emm
    0.14
    eniable
    0.14
    imer
    0.14
    olini
    0.14
    Act Density 0.008%

    No Known Activations