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

    Neuronpedia

    INDEX
    Explanations

    references to participation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.62
     }))
    -0.56
    })));
    -0.55
    )();
    -0.55
    ids
    -0.55
    })*/
    -0.55
    licability
    -0.55
    Portale
    -0.55
     reliance
    -0.54
     recourse
    -0.53
    POSITIVE LOGITS
     discussions
    0.80
     debates
    0.74
    discussions
    0.70
     shaping
    0.68
     proceedings
    0.64
     aktiviteter
    0.63
     createSlice
    0.63
     Discussions
    0.60
     activities
    0.59
     fray
    0.59
    Act Density 0.330%

    No Known Activations