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

    Neuronpedia

    INDEX
    Explanations

    statements of acceptance or agreement related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vru
    -0.44
     protoimpl
    -0.43
     dormitórios
    -0.40
     bepaalde
    -0.40
     ModelExpression
    -0.39
     poils
    -0.37
     zoude
    -0.37
     fornece
    -0.36
     gedrag
    -0.36
     gräns
    -0.35
    POSITIVE LOGITS
     okay
    0.84
     genre
    0.71
    okay
    0.66
    mean
    0.64
     OKAY
    0.64
    earth
    0.63
    Earl
    0.62
     genres
    0.61
    Okay
    0.59
     Earl
    0.59
    Act Density 0.281%

    No Known Activations