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

    Neuronpedia

    INDEX
    Explanations

    expressions of absolute negativity or dismissal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EditorBrowsable
    -0.43
    BindingResult
    -0.42
    
    -0.41
    istoitu
    -0.41
    Alguien
    -0.41
     PERSONS
    -0.41
    pantaloni
    -0.41
     gyhoeddwyd
    -0.40
    pendenti
    -0.40
     Seelen
    -0.40
    POSITIVE LOGITS
     todos
    0.54
     itſelf
    0.54
    ><><
    0.53
     poffe
    0.52
     Todos
    0.52
     poffible
    0.50
    todos
    0.50
    $_['
    0.49
    ->___
    0.47
    Todos
    0.47
    Act Density 0.146%

    No Known Activations