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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation, necessity, or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.71
     termica
    -0.58
    opsida
    -0.58
    UniformLocation
    -0.56
     Chriftian
    -0.56
     /\.
    -0.56
    CloseOperation
    -0.55
     pérd
    -0.54
    ize
    -0.53
     alimentaires
    -0.53
    POSITIVE LOGITS
     also
    1.17
     indeed
    1.10
     not
    1.04
     certainly
    1.02
     always
    1.01
     definitely
    0.99
     surely
    0.94
     actually
    0.93
     somehow
    0.91
     still
    0.87
    Act Density 0.529%

    No Known Activations