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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and suggestions for engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mos
    -0.18
     Ban
    -0.18
    alt
    -0.17
    866
    -0.15
    era
    -0.15
    adil
    -0.15
    oro
    -0.15
     Triangle
    -0.15
     hex
    -0.15
     Bennett
    -0.15
    POSITIVE LOGITS
    ahoma
    0.18
    gba
    0.17
    uffs
    0.17
    STALL
    0.16
    VRT
    0.16
    ecies
    0.16
    @js
    0.16
     eldre
    0.16
     >>↵↵
    0.15
    ispens
    0.15
    Act Density 0.179%

    No Known Activations