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

    Neuronpedia

    INDEX
    Explanations

    instances of hypocrisy in opinions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.56
     للاسماء
    -0.52
     nakalista
    -0.48
    lorette
    -0.46
     SwitchCompat
    -0.46
     surla
    -0.44
    Życiorys
    -0.44
     вікі
    -0.43
     toJson
    -0.41
     Chwiliwch
    -0.41
    POSITIVE LOGITS
     pupils
    0.71
     Pupil
    0.69
     pupil
    0.65
    Pup
    0.65
     governors
    0.63
     Pupils
    0.62
     KS
    0.60
     provision
    0.60
     SEN
    0.59
     SEND
    0.58
    Act Density 0.205%

    No Known Activations