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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ossus
    -0.63
    iop
    -0.61
    clusive
    -0.60
     Thumbnails
    -0.59
    afia
    -0.58
    ciating
    -0.58
    idem
    -0.56
    onian
    -0.55
     grasp
    -0.55
    phis
    -0.55
    POSITIVE LOGITS
    fitting
    0.91
    fall
    0.89
    fit
    0.89
     appreciated
    0.89
     prohib
    0.86
     able
    0.85
    fits
    0.84
     forgiven
    0.84
     unthinkable
    0.81
     preferable
    0.80
    Act Density 0.111%

    No Known Activations