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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desire or intent followed by infinitive verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Extras
    -0.15
    ady
    -0.14
    layer
    -0.14
    oulder
    -0.14
    oud
    -0.14
    AKE
    -0.13
    ater
    -0.13
    dy
    -0.13
    uner
    -0.13
    ÑĢеб
    -0.13
    POSITIVE LOGITS
    äºŃ
    0.16
    igr
    0.16
    gnore
    0.15
    æ²¢
    0.15
    ITERAL
    0.15
     Windsor
    0.14
     бÑĥдÑĮ
    0.14
    оÑĢалÑĮ
    0.14
    675
    0.14
    alta
    0.14
    Act Density 0.030%

    No Known Activations