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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'diss' or variations of the word 'dissolve'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Goff
    -0.76
     looted
    -0.70
    glers
    -0.65
    Reloaded
    -0.63
     Werewolf
    -0.63
    Reviewer
    -0.63
     buck
    -0.62
    tt
    -0.60
    âĹ¼
    -0.60
     strings
    -0.60
    POSITIVE LOGITS
    imilar
    1.57
    ipation
    1.49
    ociation
    1.47
    ociated
    1.44
    olving
    1.42
    olves
    1.39
    ident
    1.35
    oci
    1.32
    olute
    1.32
    ension
    1.30
    Act Density 0.022%

    No Known Activations