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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conveying difficult news or messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.88
     resourceCulture
    -0.66
    -------
    -0.63
     cherchés
    -0.62
     Audiodateien
    -0.62
    tvguidetime
    -0.62
    Autoritní
    -0.60
    enumii
    -0.60
    ymce
    -0.59
    providedIn
    -0.59
    POSITIVE LOGITS
     announcement
    0.60
     news
    0.58
     noticia
    0.56
     jub
    0.54
     overjoyed
    0.54
     announce
    0.54
     rejoice
    0.53
     announ
    0.53
     joy
    0.52
     surprise
    0.52
    Act Density 0.196%

    No Known Activations