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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors that convey varying degrees of intensity or qualities of emotions and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyh
    -0.18
    174
    -0.15
    ieves
    -0.15
    /=
    -0.15
    LastError
    -0.14
    коÑĢиÑģÑĤ
    -0.14
    ObjectContext
    -0.13
     Degrees
    -0.13
    к
    -0.13
    #
    -0.13
    POSITIVE LOGITS
    ness
    0.42
     approach
    0.36
     nature
    0.34
     attitude
    0.30
     tone
    0.30
     manner
    0.29
     Approach
    0.27
    nature
    0.27
    NESS
    0.26
     spirit
    0.26
    Act Density 0.184%

    No Known Activations