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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their associated states of being or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uba
    -0.14
    iana
    -0.14
    zo
    -0.14
     gì
    -0.14
     Acquisition
    -0.14
    ZO
    -0.14
    did
    -0.13
    ι
    -0.13
    tro
    -0.13
    icies
    -0.13
    POSITIVE LOGITS
     becoming
    0.19
     happening
    0.18
     termed
    0.16
     essentially
    0.16
     jinak
    0.15
    adaÅŁ
    0.15
     otherwise
    0.15
     become
    0.15
     intents
    0.15
    otherwise
    0.15
    Act Density 0.031%

    No Known Activations