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

    Neuronpedia

    INDEX
    Explanations

    phrases that express criticism or evaluation of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.46
     společnost
    -0.45
     funkcjon
    -0.44
     registered
    -0.41
    спонд
    -0.41
     mukana
    -0.41
     rencontres
    -0.40
     saites
    -0.40
     spoloč
    -0.40
     příslu
    -0.40
    POSITIVE LOGITS
     overrated
    0.65
    Injuries
    0.61
     Injuries
    0.60
    juries
    0.59
     injuries
    0.56
     fucking
    0.56
     stats
    0.53
     fuckin
    0.52
     beating
    0.51
     idk
    0.51
    Act Density 0.261%

    No Known Activations