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

    Neuronpedia

    INDEX
    Explanations

    words related to depth, intensity, and characteristics of physical or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.19
    INGS
    -0.17
    alles
    -0.16
    dech
    -0.15
    ings
    -0.15
     Epoch
    -0.14
    illas
    -0.14
    ABLE
    -0.14
    dej
    -0.14
    plete
    -0.14
    POSITIVE LOGITS
    ened
    0.72
    ening
    0.71
    ener
    0.54
    ens
    0.49
    eners
    0.47
    en
    0.42
    enin
    0.34
    ENER
    0.33
    ENS
    0.33
    EN
    0.31
    Act Density 0.051%

    No Known Activations