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

    Neuronpedia

    INDEX
    Explanations

    contrastive phrases that highlight differences between subjects or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.68
    ystemet
    -0.67
     NSCoder
    -0.67
    zzleHttp
    -0.66
    ************/
    -0.65
     tartalomajánló
    -0.65
     bezeichneter
    -0.64
     CURIAM
    -0.63
     @"/
    -0.63
     subconscious
    -0.62
    POSITIVE LOGITS
    Whereas
    0.82
     Whereas
    0.73
    Unlike
    0.68
     unlike
    0.67
     Unlike
    0.63
    Whilst
    0.59
    unlike
    0.58
     Mentre
    0.55
     Mientras
    0.54
    )))));
    0.53
    Act Density 0.107%

    No Known Activations