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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    genomen
    -0.40
    Base
    -0.38
    excellents
    -0.38
     judiciaire
    -0.37
     Base
    -0.36
     littéraire
    -0.35
     hemel
    -0.34
     OnInit
    -0.34
     base
    -0.32
     skr
    -0.32
    POSITIVE LOGITS
     correcting
    0.76
     correction
    0.75
    correction
    0.71
     corrects
    0.71
     correc
    0.66
     corriger
    0.66
     Correction
    0.65
     corrected
    0.64
    corrected
    0.62
     corrections
    0.62
    Act Density 0.493%

    No Known Activations