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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IZED
    -0.18
    áct
    -0.17
    è¿·
    -0.17
    AYER
    -0.16
    istrov
    -0.15
    -ce
    -0.15
    arily
    -0.15
    ordin
    -0.15
    urator
    -0.15
    uais
    -0.15
    POSITIVE LOGITS
    ings
    0.31
    able
    0.30
    ability
    0.25
     ing
    0.22
    Ing
    0.21
    ÂŃing
    0.20
    ng
    0.20
    INGS
    0.19
    ables
    0.18
    NG
    0.18
    Act Density 0.169%

    No Known Activations