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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hidden or less visible aspects of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Catto
    -0.42
     păr
    -0.41
     Trường
    -0.41
     vorkommen
    -0.40
    sspiel
    -0.40
     trường
    -0.40
     modalidades
    -0.39
    MeasureSpec
    -0.39
    CppMethod
    -0.39
     kasarigan
    -0.39
    POSITIVE LOGITS
     behind
    1.89
     BEHIND
    1.86
     Behind
    1.86
    behind
    1.83
    Behind
    1.80
     derrière
    1.34
     detrás
    1.31
     bakom
    1.30
     dietro
    1.16
    Hinter
    1.07
    Act Density 0.078%

    No Known Activations