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

    Neuronpedia

    INDEX
    Explanations

    words related to expectations and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.92
    JoinColumn
    -0.70
    ölkerung
    -0.69
     فريبيس
    -0.68
    SBATCH
    -0.65
    </caption>
    -0.63
    GEBURTSDATUM
    -0.61
    principalColumn
    -0.59
    multer
    -0.58
    formKey
    -0.58
    POSITIVE LOGITS
     anticipate
    1.17
     anticipated
    1.14
     anticipates
    1.08
     endnu
    1.02
     anticipating
    1.01
     Already
    1.01
     noch
    0.99
    Already
    0.98
     ainda
    0.98
     jeszcze
    0.98
    Act Density 0.108%

    No Known Activations