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

    Neuronpedia

    INDEX
    Explanations

    verbs and their forms associated with states of being or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahren
    -0.15
    üz
    -0.15
    389
    -0.14
     cling
    -0.14
     continued
    -0.13
    ιÏĥÏĦή
    -0.13
    YST
    -0.13
     Rencontre
    -0.13
    ICODE
    -0.13
    igram
    -0.12
    POSITIVE LOGITS
     headed
    0.27
     ready
    0.27
     heading
    0.23
     still
    0.22
     ripe
    0.21
    ready
    0.21
     alive
    0.21
     safe
    0.19
    still
    0.19
     READY
    0.19
    Act Density 0.056%

    No Known Activations