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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the effectiveness of treatments or interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emann
    -0.15
     Vital
    -0.15
    uo
    -0.14
     Hamp
    -0.14
     Hob
    -0.14
    Spoiler
    -0.14
    uw
    -0.14
    elsea
    -0.14
    wich
    -0.13
    úsqueda
    -0.13
    POSITIVE LOGITS
    otine
    0.18
    hood
    0.16
     Decomp
    0.15
    óc
    0.15
    acy
    0.15
    pest
    0.15
    entre
    0.14
     intr
    0.14
    ants
    0.14
    ought
    0.14
    Act Density 0.010%

    No Known Activations