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

    Neuronpedia

    INDEX
    Explanations

    prepositions and related expressions indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.05
    3:0.11
    4:0.06
    5:0.20
    6:0.06
    7:0.04
    8:0.07
    9:0.10
    10:0.04
    11:0.04
    Negative Logits
     looming
    -2.57
    coming
    -2.09
     deteriorating
    -1.99
    ICES
    -1.97
    IRE
    -1.92
     forthcoming
    -1.89
     pending
    -1.81
    RG
    -1.81
    ongo
    -1.81
     impacting
    -1.79
    POSITIVE LOGITS
    ilda
    2.00
     bapt
    1.96
     Salv
    1.94
     Peb
    1.92
     Benjamin
    1.86
     Patty
    1.84
    dinand
    1.82
     Salmon
    1.72
    lator
    1.71
    aire
    1.71
    Act Density 0.000%

    No Known Activations