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

    Neuronpedia

    INDEX
    Explanations

    terms related to inquiry and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ek
    -0.18
     Eag
    -0.18
    ein
    -0.16
    osate
    -0.16
    ater
    -0.14
     tay
    -0.14
     dö
    -0.14
    aters
    -0.14
    ÅĻÃŃ
    -0.14
    woord
    -0.13
    POSITIVE LOGITS
    ings
    0.36
    ers
    0.36
    INGS
    0.29
    ERS
    0.28
    ability
    0.26
    able
    0.25
    ableObject
    0.25
    ng
    0.25
    ables
    0.24
     ing
    0.24
    Act Density 0.054%

    No Known Activations