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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dafür
    -0.76
    CDCl
    -0.61
     habit
    -0.61
    .*")]
    -0.57
    Assured
    -0.56
     Ostat
    -0.53
    ViewInit
    -0.53
    <bos>
    -0.53
    UseVisualStyle
    -0.53
    рыз
    -0.52
    POSITIVE LOGITS
     blessés
    0.70
     Normdatei
    0.66
     betale
    0.61
     découver
    0.60
     Vikipedi
    0.60
     umsch
    0.59
     prêts
    0.57
     tárgy
    0.56
     Giud
    0.56
    matmul
    0.55
    Act Density 0.312%

    No Known Activations