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

    Neuronpedia

    INDEX
    Explanations

    negative impacts or harm associated with concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases comparing two things using "more...than" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     very
    -0.53
    LElement
    -0.47
     muy
    -0.47
    very
    -0.46
     assez
    -0.44
     makeStyles
    -0.44
    StartTag
    -0.44
     mostly
    -0.43
     Enough
    -0.43
    ⇑
    -0.43
    POSITIVE LOGITS
     than
    2.92
     niż
    1.97
    Than
    1.88
     THAN
    1.88
    than
    1.87
    THAN
    1.58
     než
    1.56
     Than
    1.56
     än
    1.43
     kuin
    1.40
    Act Density 0.627%

    No Known Activations