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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.07
    3:0.09
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Unch
    -2.85
    ��
    -2.50
     Reloaded
    -2.47
     Exam
    -2.41
     Idle
    -2.35
     Spectre
    -2.35
     Binary
    -2.34
     Rating
    -2.31
     Actual
    -2.31
     Calculator
    -2.30
    POSITIVE LOGITS
     confir
    2.21
     concess
    2.12
     notor
    2.06
    liv
    2.06
     woodland
    2.05
    ollah
    2.04
    onte
    2.04
     conclud
    2.00
    sylv
    1.98
    close
    1.97
    Act Density 0.000%

    No Known Activations