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

    Neuronpedia

    INDEX
    Explanations

    future tense verbs indicating intent or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ällt
    -0.15
    itat
    -0.15
    alties
    -0.14
    elor
    -0.14
    oksen
    -0.13
    dv
    -0.13
    ussen
    -0.13
    ontent
    -0.13
    иÑĢа
    -0.13
    érique
    -0.13
    POSITIVE LOGITS
    iams
    0.29
    iam
    0.22
    kommen
    0.21
    l
    0.20
     be
    0.20
    iston
    0.16
    IAM
    0.16
    iger
    0.16
    fully
    0.15
     not
    0.15
    Act Density 0.298%

    No Known Activations