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

    Neuronpedia

    INDEX
    Explanations

    negative phrases about personal experiences or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :CGRect
    -0.17
    isible
    -0.14
    :disable
    -0.14
    ]*)
    -0.14
    ambi
    -0.13
    æk
    -0.13
    AGER
    -0.13
    pires
    -0.13
    venir
    -0.13
    _warnings
    -0.13
    POSITIVE LOGITS
     have
    0.51
     need
    0.50
     has
    0.49
     must
    0.46
     HAVE
    0.46
    need
    0.44
    have
    0.43
     needs
    0.42
     gotta
    0.42
     Have
    0.42
    Act Density 0.447%

    No Known Activations