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

    Neuronpedia

    INDEX
    Explanations

    statements starting with "If that", implying a condition or scenario

    oai_token-act-pair · gpt-3.5-turbo

    phrases and clauses that suggest conditional statements or hypotheticals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.67
    indal
    -0.61
    ngth
    -0.60
    iband
    -0.60
    IOR
    -0.59
    Effective
    -0.58
    interstitial
    -0.58
    igmatic
    -0.57
    ©¶æ¥µ
    -0.57
    HUD
    -0.56
    POSITIVE LOGITS
     weren
    1.54
     were
    1.16
    were
    1.10
     hadn
    1.09
     happens
    1.02
     bothers
    0.99
     pans
    0.98
     fails
    0.98
     succeeds
    0.98
     ain
    0.94
    Act Density 0.173%

    No Known Activations